INDEX

Explanations

specific text ornaments or separators used in the text

oai_token-act-pair · gpt-3.5-turbo

proper nouns and titles of productions or works

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

 tremend

-0.94

 eleph

-0.71

aditional

-0.68

hement

-0.68

 citiz

-0.66

oun

-0.63

 occas

-0.62

 representation

-0.61

 grid

-0.61

 undermin

-0.61

POSITIVE LOGITS

↵

0.93

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.89

ÂłÂłÂł

0.77

Merit

0.76

ÂłÂłÂłÂłÂłÂłÂłÂł

0.75

Premium

0.72

posted

0.72

minster

0.72

Population

0.72

Synopsis

0.71

Activations Density 0.248%

specific text ornaments or separators used in the text

proper nouns and titles of productions or works

No Comments

No Known Activations