INDEX

Explanations

phrases related to violent actions or situations

oai_token-act-pair · gpt-3.5-turbo

phrases describing violent actions and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 veto

-0.70

 postponed

-0.63

allowed

-0.62

eton

-0.62

hur

-0.62

orea

-0.61

cens

-0.61

 offensively

-0.60

 vetoed

-0.58

chall

-0.58

POSITIVE LOGITS

 Pieces

1.01

 pieces

0.88

 paste

0.84

 fragments

0.84

 rubble

0.80

utonium

0.80

 shred

0.79

ãĤ©

0.76

ffee

0.73

 powder

0.71

Activations Density 0.251%

phrases related to violent actions or situations

phrases describing violent actions and their consequences

No Comments

No Known Activations