INDEX

Explanations

proper nouns of people or places

oai_token-act-pair · gpt-3.5-turbo

references to specific entities and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

RON

-0.80

ACTED

-0.76

lements

-0.73

TOR

-0.72

ten

-0.70

TRI

-0.69

Toronto

-0.69

TOR

-0.69

-0.68

POSITIVE LOGITS

itt

1.10

ayn

0.84

ich

0.82

icho

0.79

igh

0.79

 Nichols

0.78

gh

0.76

PP

0.75

icht

0.74

ina

0.73

Activations Density 0.460%

proper nouns of people or places

references to specific entities and numerical data

No Comments

No Known Activations