INDEX

Explanations

words related to unpleasant or negative situations

oai_token-act-pair · gpt-3.5-turbo

gerunds and present participles ending in 'ing' and similar forms, indicating ongoing actions

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

Gim

-0.65

Legend

-0.63

eve

-0.62

ãĥĨãĤ£

-0.60

Vel

-0.59

peria

-0.59

oval

-0.59

IDENT

-0.58

option

-0.58

RM

-0.58

POSITIVE LOGITS

anwhile

0.86

hower

0.72

uffs

0.72

geist

0.71

 clouds

0.66

 heap

0.66

imates

0.66

arella

0.65

 synthes

0.65

nib

0.65

Activations Density 0.268%

words related to unpleasant or negative situations

gerunds and present participles ending in 'ing' and similar forms, indicating ongoing actions

No Comments

No Known Activations