INDEX

Explanations

phrases or words related to decisions or actions involving a choice between two possibilities

oai_token-act-pair · gpt-3.5-turbo

components and aspects related to constructed identities or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Chambers

-0.77

Ĥª

-0.68

 Doors

-0.68

Ń·

-0.66

 prayer

-0.60

 prayers

-0.60

APTER

-0.57

 Gillespie

-0.57

 throats

-0.56

 coax

-0.56

POSITIVE LOGITS

your

0.89

export

0.81

up

0.78

time

0.76

react

0.76

luster

0.75

advertisement

0.75

ins

0.74

chart

0.74

existing

0.73

Activations Density 0.071%

phrases or words related to decisions or actions involving a choice between two possibilities

components and aspects related to constructed identities or roles

No Comments

No Known Activations