INDEX

Explanations

proper nouns and names

oai_token-act-pair · gpt-3.5-turbo

names and locations related to specific individuals and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

etheless

-0.82

ãĥ¼ãĥĨ

-0.66

PDT

-0.64

Ħ¢

-0.63

 decor

-0.62

 thous

-0.61

selves

-0.61

orney

-0.61

ievers

-0.59

mable

-0.59

POSITIVE LOGITS

esome

0.97

enhagen

0.85

itates

0.83

itating

0.82

itation

0.81

regation

0.81

itations

0.80

idad

0.78

itate

0.78

itated

0.77

Activations Density 0.017%

proper nouns and names

names and locations related to specific individuals and events

No Comments

No Known Activations