INDEX

Explanations

the word "scenario" and related terms

oai_token-act-pair · gpt-3.5-turbo

references to different possible scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ances

-0.84

itsch

-0.77

tein

-0.76

ãĤŃ

-0.76

enfranch

-0.74

emouth

-0.73

artisan

-0.73

anguages

-0.72

cott

-0.72

vation

-0.70

POSITIVE LOGITS

 scenario

1.11

 scenarios

1.06

 involving

0.90

 unfold

0.80

 unfolding

0.80

 wherein

0.78

 whereby

0.74

finder

0.72

enario

0.72

eers

0.71

Activations Density 0.037%

the word "scenario" and related terms

references to different possible scenarios

No Comments

No Known Activations