INDEX

Explanations

words related to importance or significance in a context

oai_token-act-pair · gpt-3.5-turbo

phrases that highlight the significance or function of various roles in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

arus

-0.63

urses

-0.61

results

-0.61

 Liver

-0.61

 Purg

-0.60

atri

-0.59

prus

-0.59

cffff

-0.58

 Samp

-0.58

Dream

-0.58

POSITIVE LOGITS

 role

1.03

 helping

0.96

 assisting

0.87

 influencing

0.87

 facilitating

0.86

 roles

0.85

in

0.85

 therein

0.84

 towards

0.82

 supporting

0.81

Activations Density 0.069%

words related to importance or significance in a context

phrases that highlight the significance or function of various roles in different contexts

No Comments

No Known Activations