INDEX

Explanations

mentions of the word "Little"

oai_token-act-pair · gpt-3.5-turbo

references to "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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ktop

-0.82

icular

-0.81

ãĥķãĤ©

-0.79

âķĲâķĲ

-0.79

CoC

-0.79

 conclud

-0.74

ickr

-0.74

inates

-0.73

antage

-0.72

senal

-0.71

POSITIVE LOGITS

finger

0.91

 Bird

0.86

Brother

0.85

 Debbie

0.80

wood

0.80

 Brother

0.79

woods

0.79

bird

0.78

 Sisters

0.78

Boy

0.78

Activations Density 0.012%

mentions of the word "Little"

references to "Little" in various contexts

No Comments

No Known Activations