INDEX

Explanations

words associated with expressions of dissatisfaction or complaint

oai_token-act-pair · gpt-3.5-turbo

variations of the verb "to be" and related states or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 appropri

-0.80

ãĥ¯ãĥ³

-0.75

Buk

-0.66

ãĥĵ

-0.65

committee

-0.63

 handc

-0.63

 guerrilla

-0.59

UNE

-0.59

 borrowing

-0.58

 improv

-0.57

POSITIVE LOGITS

thood

0.87

qt

0.85

omed

0.83

owered

0.79

olves

0.77

ilus

0.76

oused

0.75

obbies

0.75

athed

0.72

cies

0.72

Activations Density 0.043%

words associated with expressions of dissatisfaction or complaint

variations of the verb "to be" and related states or conditions

No Comments

No Known Activations