INDEX

Explanations

phrases describing hypothetical or symbolic scenarios

oai_token-act-pair · gpt-3.5-turbo

statements or phrases that convey hypothetical or conditional scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

"><

-0.70

"]=>

-0.69

idates

-0.68

adra

-0.66

 Airl

-0.61

vere

-0.59

byn

-0.58

izabeth

-0.57

 couples

-0.56

 quickest

-0.55

POSITIVE LOGITS

paste

0.71

 invincible

0.69

Ãł

0.68

pi

0.66

 existed

0.65

ti

0.65

Ãĥ

0.63

rael

0.61

paren

0.61

 SECTION

0.61

Activations Density 0.152%

phrases describing hypothetical or symbolic scenarios

statements or phrases that convey hypothetical or conditional scenarios

No Comments

No Known Activations