INDEX

Explanations

adjectives or verbs related to negation or absence

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the concept of "nothing" or the lack of action or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

essing

-0.71

pling

-0.65

ippers

-0.64

 anonymity

-0.63

sole

-0.63

cise

-0.63

rets

-0.61

NAS

-0.60

own

-0.59

igers

-0.59

POSITIVE LOGITS

 happens

1.26

 happened

1.20

 transpired

1.10

 goes

1.04

 occurs

1.02

 else

1.00

 flowed

0.94

 lasts

0.91

 went

0.91

 comes

0.90

Activations Density 0.103%

adjectives or verbs related to negation or absence

phrases emphasizing the concept of "nothing" or the lack of action or results

No Comments

No Known Activations