INDEX

Explanations

adjectives and nouns representing significant or important characteristics or aspects

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate representation or significant changes in context

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

iously

-0.70

irlf

-0.62

enson

-0.61

Wik

-0.60

 Noel

-0.58

 Myth

-0.58

ãĥ³

-0.57

 seem

-0.57

 assum

-0.57

 Rusty

-0.57

POSITIVE LOGITS

POS

0.77

 culmination

0.76

upper

0.71

INAL

0.69

uras

0.67

 pinnacle

0.66

ICAN

0.65

rial

0.65

amount

0.65

eta

0.64

Activations Density 0.163%

adjectives and nouns representing significant or important characteristics or aspects

phrases that indicate representation or significant changes in context

No Comments

No Known Activations