INDEX

Explanations

words related to specific actions or instructions

oai_token-act-pair · gpt-3.5-turbo

words or phrases indicating key actions or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

©¶æ¥µ

-0.69

ccording

-0.64

cius

-0.62

 metic

-0.59

 entreprene

-0.58

umin

-0.58

uc

-0.56

sv

-0.55

Ö¼

-0.54

visible

-0.54

POSITIVE LOGITS

for

1.37

for

1.27

FOR

1.18

FOR

1.13

For

0.99

For

0.97

fore

0.81

fort

0.81

fro

0.74

FORE

0.67

Activations Density 0.134%

words related to specific actions or instructions

words or phrases indicating key actions or decisions

No Comments

No Known Activations