INDEX

Explanations

words related to causing harm or pain

oai_token-act-pair · gpt-3.5-turbo

terms associated with causing harm or injury

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

Ou

-0.86

wagen

-0.84

runner

-0.79

cube

-0.74

cius

-0.73

clinton

-0.65

elling

-0.65

chrom

-0.64

 McKenna

-0.64

 Monaco

-0.63

POSITIVE LOGITS

 inflicted

1.01

 inflic

0.91

 wounds

0.88

 inflicting

0.87

 inflict

0.85

hesda

0.85

 havoc

0.85

lehem

0.81

 veter

0.80

olon

0.80

Activations Density 0.023%

words related to causing harm or pain

terms associated with causing harm or injury

No Comments

No Known Activations