INDEX

Explanations

phrases indicating impossibility or negative outcomes

oai_token-act-pair · gpt-3.5-turbo

phrases expressing impossibility or no means of achieving something

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

uster

-0.86

ĪĴ

-0.79

anmar

-0.77

erville

-0.77

igel

-0.76

itton

-0.75

usters

-0.74

 livest

-0.73

erva

-0.73

asts

-0.72

POSITIVE LOGITS

 whatsoever

1.11

point

0.85

fare

0.83

aterasu

0.80

WAY

0.72

DAM

0.71

ANY

0.71

finding

0.69

YP

0.69

Way

0.68

Activations Density 0.020%

phrases indicating impossibility or negative outcomes

phrases expressing impossibility or no means of achieving something

No Comments

No Known Activations