INDEX

Explanations

references to the phrase "Little [X]", where X can be a variety of words

oai_token-act-pair · gpt-3.5-turbo

references to the term "Little" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

CoC

-0.79

ãĥķãĤ©

-0.75

inates

-0.74

 conclud

-0.73

 confir

-0.71

âķĲâķĲ

-0.70

ktop

-0.70

anwhile

-0.68

EMENT

-0.68

antage

-0.68

POSITIVE LOGITS

finger

0.92

Brother

0.86

john

0.84

 Debbie

0.84

bird

0.84

 Bird

0.82

woods

0.79

 Sisters

0.78

 Brother

0.76

 Sister

0.75

Activations Density 0.015%

references to the phrase "Little [X]", where X can be a variety of words

references to the term "Little" in various contexts

No Comments

No Known Activations