INDEX

Explanations

requests for action or assistance

oai_token-act-pair · gpt-3.5-turbo

requests or prompts for action

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

MpServer

-0.83

lings

-0.78

arc

-0.74

cler

-0.70

é¾

-0.66

ual

-0.66

ignty

-0.66

ylum

-0.66

senal

-0.65

 Huntington

-0.64

POSITIVE LOGITS

 advise

0.95

 excuse

0.94

 ignore

0.91

 forgive

0.90

 fill

0.90

 Ignore

0.88

 refrain

0.86

 note

0.86

 circulate

0.84

 feel

0.82

Activations Density 0.016%

requests for action or assistance

requests or prompts for action

No Comments

No Known Activations