INDEX

Explanations

adjectives followed by numbers indicating quantity or importance

oai_token-act-pair · gpt-3.5-turbo

important descriptors or adjectives indicating significance or magnitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

someone

-0.91

antry

-0.82

urgy

-0.81

expression

-0.76

ylum

-0.75

cture

-0.71

actionDate

-0.69

ulture

-0.69

activity

-0.69

culation

-0.69

POSITIVE LOGITS

 paragraphs

1.11

 categories

1.09

 generations

1.06

 thirds

1.04

 pairs

1.03

 versions

1.01

 batches

1.01

 editions

0.99

 fronts

0.99

 districts

0.99

Activations Density 0.214%

adjectives followed by numbers indicating quantity or importance

important descriptors or adjectives indicating significance or magnitude

No Comments

No Known Activations