INDEX

Explanations

phrases or words related to conclusions, endings, or finality

oai_token-act-pair · gpt-3.5-turbo

references to endings or conclusions

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

æ©Ł

-0.70

onson

-0.68

ufact

-0.65

BLIC

-0.65

itsch

-0.64

htaking

-0.64

thouse

-0.62

Dou

-0.61

urry

-0.61

hee

-0.60

POSITIVE LOGITS

owment

1.34

angering

1.20

game

0.98

orph

0.95

ocrine

0.92

ocrin

0.92

angers

0.91

angered

0.91

urance

0.83

oscopic

0.81

Activations Density 0.036%

phrases or words related to conclusions, endings, or finality

references to endings or conclusions

No Comments

No Known Activations