INDEX

Explanations

mentions of the term "ats" followed by numbers representing different actions or concepts

oai_token-act-pair · gpt-3.5-turbo

mentions of cats

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

 sclerosis

-0.79

SOURCE

-0.76

OUS

-0.72

ADE

-0.66

 rall

-0.64

SPONSORED

-0.63

ufact

-0.63

shire

-0.62

 whence

-0.62

 Tsukuyomi

-0.61

POSITIVE LOGITS

wana

1.09

hirt

1.07

pace

1.06

heet

1.05

rix

0.98

awan

0.97

terson

0.97

hematic

0.96

chet

0.94

hemat

0.92

Activations Density 0.018%

mentions of the term "ats" followed by numbers representing different actions or concepts

mentions of cats

No Comments

No Known Activations