INDEX

Explanations

words related to intense emotional states or conditions

oai_token-act-pair · gpt-3.5-turbo

terms related to performance and specifications, particularly in medical or technical contexts

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

-0.71

 Carbuncle

-0.71

hes

-0.66

undo

-0.64

ourced

-0.63

ãĤ¸

-0.63

iami

-0.63

estation

-0.62

ADRA

-0.62

osp

-0.62

POSITIVE LOGITS

manent

0.96

monkey

0.92

nel

0.88

intendent

0.87

due

0.87

ior

0.84

stein

0.82

taining

0.80

agus

0.80

hood

0.79

Activations Density 0.046%

words related to intense emotional states or conditions

terms related to performance and specifications, particularly in medical or technical contexts

No Comments

No Known Activations