INDEX

Explanations

the word "no" followed by a high number

oai_token-act-pair · gpt-3.5-turbo

negative phrases indicating the absence or lack of something

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

dor

-0.68

dry

-0.68

sth

-0.67

staking

-0.67

rn

-0.65

ials

-0.63

elli

-0.63

lycer

-0.59

Untitled

-0.59

RAFT

-0.59

POSITIVE LOGITS

xious

1.07

 matter

0.96

 longer

0.91

terday

0.87

 indication

0.87

etheless

0.87

 sooner

0.84

 conceivable

0.83

 doubt

0.81

 conclusive

0.80

Activations Density 0.096%

the word "no" followed by a high number

negative phrases indicating the absence or lack of something

No Comments

No Known Activations