INDEX

Explanations

words related to specific movie titles and characters

oai_token-act-pair · gpt-3.5-turbo

references to specific entities or titles related to movies, literature, and notable organizations or locations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

terday

-0.71

 customers

-0.68

 conflic

-0.60

uddenly

-0.58

 pupils

-0.58

 shoppers

-0.57

 learners

-0.56

munition

-0.56

 borrowers

-0.56

 waivers

-0.55

POSITIVE LOGITS

liest

0.91

iest

0.81

osphere

0.80

mma

0.76

venth

0.75

est

0.74

cients

0.71

 Presidency

0.69

adle

0.67

 Legislature

0.67

Activations Density 0.437%

words related to specific movie titles and characters

references to specific entities or titles related to movies, literature, and notable organizations or locations

No Comments

No Known Activations