INDEX

Explanations

phrases indicating intensity or comparison

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the concept of minimization or a lower bound

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kefeller

-0.70

xs

-0.69

rows

-0.68

inal

-0.63

borg

-0.63

asms

-0.63

gaard

-0.61

dal

-0.59

cats

-0.59

stocks

-0.58

POSITIVE LOGITS

Gi

0.77

 suffice

0.71

Lago

0.70

orah

0.68

FontSize

0.65

agogue

0.63

 provocation

0.62

 assume

0.62

ruck

0.60

taining

0.60

Activations Density 0.037%

phrases indicating intensity or comparison

phrases emphasizing the concept of minimization or a lower bound

No Comments

No Known Activations