INDEX

Explanations

phrases or words related to significant points or important elements

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize key moments or important features in a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

thood

-0.75

aah

-0.72

zin

-0.72

itte

-0.71

nery

-0.69

atern

-0.69

entric

-0.69

nian

-0.67

sett

-0.66

onew

-0.65

POSITIVE LOGITS

 highlights

0.99

 reel

0.94

ibilities

0.81

TextColor

0.81

 Highlights

0.79

ibility

0.79

 highlighting

0.77

ãĤ¤ãĥĪ

0.75

umenthal

0.74

iary

0.71

Activations Density 0.019%

phrases or words related to significant points or important elements

phrases that emphasize key moments or important features in a narrative

No Comments

No Known Activations