INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "key" or related variations within the text

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

 Vaugh

-0.69

uates

-0.68

uum

-0.67

encer

-0.66

ews

-0.66

ATIONAL

-0.65

Interstitial

-0.64

ATIONS

-0.63

uating

-0.61

 Surviv

-0.60

POSITIVE LOGITS

*/(

1.06

hole

0.94

ilant

0.87

boards

0.85

words

0.84

pad

0.82

stroke

0.82

holes

0.80

hoe

0.80

ring

0.79

Activations Density 0.015%

proper nouns

occurrences of the term "key" or related variations within the text

No Comments

No Known Activations