INDEX

Explanations

terms related to intimidation and harassment

oai_token-act-pair · gpt-3.5-turbo

instances of the word "intimidation" and its variations

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

Foot

-0.78

pring

-0.78

night

-0.77

alach

-0.73

orah

-0.73

inet

-0.72

ilver

-0.72

ether

-0.71

LEASE

-0.71

noon

-0.70

POSITIVE LOGITS

 tactics

0.96

 intimidation

0.96

 intimidated

0.95

 intimid

0.84

 coer

0.81

 stalking

0.81

 retaliation

0.80

 intimidate

0.76

ingly

0.75

 repr

0.74

Activations Density 0.036%

terms related to intimidation and harassment

instances of the word "intimidation" and its variations

No Comments

No Known Activations