INDEX

Explanations

words related to conflict or confrontation

oai_token-act-pair · gpt-3.5-turbo

instances of conflict or confrontation

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

employment

-0.82

mental

-0.81

enfranch

-0.80

intestinal

-0.77

duct

-0.76

secut

-0.74

requisite

-0.73

©¶æ

-0.69

ufact

-0.69

¥µ

-0.68

POSITIVE LOGITS

halla

0.99

 clash

0.92

roy

0.79

 between

0.78

 Ambro

0.77

 looms

0.76

 clashes

0.74

mosp

0.72

 Amon

0.70

 Royale

0.70

Activations Density 0.014%

words related to conflict or confrontation

instances of conflict or confrontation

No Comments

No Known Activations