INDEX

Explanations

specific situations or events described as scenarios

oai_token-act-pair · gpt-3.5-turbo

references to hypothetical situations or scenarios

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

enfranch

-0.80

anguages

-0.80

alties

-0.78

ighters

-0.78

obe

-0.76

igion

-0.74

olulu

-0.74

ixed

-0.74

artney

-0.74

emouth

-0.74

POSITIVE LOGITS

 scenarios

0.95

 scenario

0.94

 involving

0.78

eers

0.77

 unfold

0.72

0.71

 unfolding

0.71

ttes

0.65

 Situation

0.64

Activations Density 0.020%

specific situations or events described as scenarios

references to hypothetical situations or scenarios

No Comments

No Known Activations