INDEX

Explanations

words related to literature or literary concepts

oai_token-act-pair · gpt-3.5-turbo

references to literary concepts or themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

rals

-0.81

lain

-0.79

akening

-0.79

ned

-0.76

xon

-0.72

alin

-0.70

ls

-0.70

olen

-0.68

ldon

-0.66

ns

-0.65

POSITIVE LOGITS

 literary

1.10

 fiction

0.96

 Literary

0.94

 Fiction

0.92

writer

0.87

 Writers

0.86

 Writer

0.85

fiction

0.81

 RELE

0.79

 laureate

0.79

Activations Density 0.014%

words related to literature or literary concepts

references to literary concepts or themes

No Comments

No Known Activations