INDEX

Explanations

terms related to jars or containers

oai_token-act-pair · gpt-3.5-turbo

mentions of jars or similar containers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ãģį

-0.72

ingham

-0.72

 Eleven

-0.70

ATK

-0.68

 Eater

-0.66

imates

-0.63

 Punk

-0.61

BOOK

-0.59

ATL

-0.59

SPD

-0.58

POSITIVE LOGITS

jar

1.34

zan

0.98

rod

0.92

Jar

0.91

rez

0.87

van

0.85

akia

0.85

bled

0.85

azz

0.84

rar

0.81

Activations Density 0.007%

terms related to jars or containers

mentions of jars or similar containers

No Comments

No Known Activations