INDEX

Explanations

numerical expressions with a specific formatting pattern

oai_token-act-pair · gpt-3.5-turbo

occurrences of the number three

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

staking

-0.82

rolet

-0.72

sym

-0.68

esville

-0.68

numbered

-0.58

 mell

-0.58

 Suzuki

-0.58

FontSize

-0.57

trak

-0.56

knife

-0.56

POSITIVE LOGITS

rd

2.11

RD

1.17

DS

0.96

dfx

0.96

peat

0.88

Aren

0.86

 cheers

0.80

DP

0.79

PO

0.79

RF

0.77

Activations Density 0.091%

numerical expressions with a specific formatting pattern

occurrences of the number three

No Comments

No Known Activations