INDEX

Explanations

mentions of autographs or signing items

oai_token-act-pair · gpt-3.5-turbo

references to autographs

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

UTION

-0.85

IRO

-0.83

 Soda

-0.81

RAFT

-0.80

BE

-0.79

mary

-0.79

ENCE

-0.78

ISION

-0.78

FORE

-0.76

ptives

-0.76

POSITIVE LOGITS

ographs

1.26

ograph

1.21

ographed

1.09

aut

1.04

iques

0.99

istically

0.98

ocom

0.93

archs

0.91

umn

0.91

ogyn

0.89

Activations Density 0.008%

mentions of autographs or signing items

references to autographs

No Comments

No Known Activations