INDEX

Explanations

scenarios or hypothetical situations

oai_token-act-pair · gpt-3.5-turbo

phrases or mentions of potential situations or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ighters

-0.91

anguages

-0.85

olulu

-0.82

emouth

-0.79

inking

-0.78

ove

-0.76

igion

-0.75

ighter

-0.75

obe

-0.75

ixed

-0.75

POSITIVE LOGITS

 scenario

0.97

 scenarios

0.97

0.76

 involving

0.75

 unfold

0.72

eers

0.72

0.71

0.69

0.67

 unfolding

0.66

Activations Density 0.016%

scenarios or hypothetical situations

phrases or mentions of potential situations or conditions

No Comments

No Known Activations