INDEX

Explanations

photographs or images indicated in the context

oai_token-act-pair · gpt-3.5-turbo

references to photographs or visual content

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

ensable

-0.81

oler

-0.80

rencies

-0.76

merce

-0.75

osc

-0.74

elling

-0.73

iazep

-0.71

resses

-0.70

itability

-0.70

powers

-0.70

POSITIVE LOGITS

 Courtesy

0.92

 Photo

0.91

 illustration

0.87

Photo

0.85

journal

0.83

 courtesy

0.81

 Credit

0.81

 Editing

0.75

 Photographer

0.74

Credit

0.73

Activations Density 0.016%

photographs or images indicated in the context

references to photographs or visual content

No Comments

No Known Activations