INDEX

Explanations

phrases related to small physical objects

oai_token-act-pair · gpt-3.5-turbo

articles or quantifiers in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Effects

-0.84

etsk

-0.82

iments

-0.80

ATURES

-0.77

arten

-0.76

izons

-0.76

words

-0.75

ItemTracker

-0.75

inson

-0.75

Examples

-0.73

POSITIVE LOGITS

 single

0.87

 nutshell

0.82

 century

0.82

 dozen

0.81

 defunct

0.79

 gigantic

0.78

 typical

0.77

 particular

0.76

 larger

0.75

 thousand

0.75

Activations Density 0.227%

phrases related to small physical objects

articles or quantifiers in various contexts

No Comments

No Known Activations