INDEX

Explanations

reflexive pronouns or verbs indicating an action taken by the subject on itself

oai_token-act-pair · gpt-3.5-turbo

references to self-focused language

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onal

-0.73

emis

-0.64

heny

-0.64

origin

-0.63

grade

-0.60

 Vine

-0.58

 Booth

-0.57

illery

-0.57

 Alger

-0.56

ion

-0.56

POSITIVE LOGITS

ortium

0.72

 submar

0.65

ãĥķ

0.65

 acquainted

0.65

agos

0.64

ãĤĭ

0.64

çīĪ

0.64

 è£ıè

0.63

ãģı

0.63

 accommod

0.63

Activations Density 0.044%

reflexive pronouns or verbs indicating an action taken by the subject on itself

references to self-focused language

No Comments

No Known Activations