INDEX

Explanations

phrases related to influence, inspiration, or emulation

oai_token-act-pair · gpt-3.5-turbo

references to comparisons and adaptations of concepts or entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

essed

-0.72

bit

-0.68

Bound

-0.66

bart

-0.66

å¥³

-0.66

verning

-0.65

ointed

-0.64

BF

-0.64

Wind

-0.61

numbered

-0.61

POSITIVE LOGITS

 classic

0.90

 stereotypical

0.90

 traditional

0.84

 typical

0.83

 tropes

0.79

 clich

0.77

 stereotypes

0.75

 classical

0.75

 ante

0.72

classic

0.71

Activations Density 0.359%

phrases related to influence, inspiration, or emulation

references to comparisons and adaptations of concepts or entities

No Comments

No Known Activations