INDEX

Explanations

words related to baseball such as 'bat'

oai_token-act-pair · gpt-3.5-turbo

references to bats

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

ãĥ´ãĤ¡

-0.97

xia

-0.77

FINE

-0.75

zanne

-0.71

Ô

-0.65

eous

-0.65

 Publisher

-0.65

vre

-0.65

oppable

-0.63

éĸ

-0.63

POSITIVE LOGITS

tered

0.90

bat

0.80

manship

0.78

bat

0.77

chers

0.76

ista

0.75

oche

0.75

bats

0.74

hit

0.73

cher

0.72

Activations Density 0.012%

words related to baseball such as 'bat'

references to bats

No Comments

No Known Activations