INDEX

Explanations

keywords related to vigilance and vigilant actions

oai_token-act-pair · gpt-3.5-turbo

mentions of vigilantism and related concepts

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

fixed

-0.78

HF

-0.75

minus

-0.74

NetMessage

-0.73

cloth

-0.71

 lowly

-0.70

berman

-0.69

hare

-0.69

laden

-0.68

Commerce

-0.66

POSITIVE LOGITS

 vigilant

0.92

urnal

0.84

 vigilance

0.83

ignt

0.80

 vigil

0.79

igil

0.77

 patrolling

0.73

ism

0.72

iously

0.72

ante

0.70

Activations Density 0.028%

keywords related to vigilance and vigilant actions

mentions of vigilantism and related concepts

No Comments

No Known Activations