INDEX

Explanations

personal pronouns and verbs related to actions towards others

oai_token-act-pair · gpt-3.5-turbo

references to individuals and their relationships in a narrative context

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

NetMessage

-0.72

 largeDownload

-0.71

heny

-0.61

 Variety

-0.58

 Ruff

-0.57

PLA

-0.57

mega

-0.56

 Memor

-0.56

inelli

-0.55

 Federation

-0.55

POSITIVE LOGITS

selves

1.16

self

0.92

atic

0.85

atically

0.83

atics

0.77

 senseless

0.76

alian

0.73

 unconscious

0.73

 selves

0.72

 asleep

0.70

Activations Density 0.216%

personal pronouns and verbs related to actions towards others

references to individuals and their relationships in a narrative context

No Comments

No Known Activations