INDEX

Explanations

Roman numerals associated with particular phrases or words

oai_token-act-pair · gpt-3.5-turbo

references to structured categories or classifications, especially in relation to entertainment, volumes, and historical figures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

uckland

-0.70

heed

-0.60

TAM

-0.59

mouth

-0.59

 dent

-0.58

tem

-0.58

panic

-0.56

Teg

-0.55

chance

-0.55

expensive

-0.55

POSITIVE LOGITS

III

1.98

VII

1.86

II

1.85

 VIII

1.85

IV

1.83

III

1.82

VI

1.78

II

1.73

XII

1.69

VII

1.66

Activations Density 0.310%

Roman numerals associated with particular phrases or words

references to structured categories or classifications, especially in relation to entertainment, volumes, and historical figures

No Comments

No Known Activations