INDEX

Explanations

phrases related to expressing opinions or beliefs

oai_token-act-pair · gpt-3.5-turbo

references to personal opinions or viewpoints

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

 Mamm

-0.77

trap

-0.73

ursed

-0.65

Sequ

-0.62

 Maid

-0.62

 Dent

-0.60

 Reflex

-0.60

amaz

-0.60

moon

-0.58

ALL

-0.58

POSITIVE LOGITS

yip

0.96

 opinions

0.91

 views

0.91

 viewpoints

0.88

hops

0.86

 guiActiveUn

0.80

 beliefs

0.79

rences

0.78

chool

0.78

reprene

0.77

Activations Density 0.026%

phrases related to expressing opinions or beliefs

references to personal opinions or viewpoints

No Comments

No Known Activations