INDEX

Explanations

words related to dirtiness or degradation

oai_token-act-pair · gpt-3.5-turbo

occurrences of the prefix "gr," particularly in a context of describing negative traits or situations

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

phrine

-0.73

 Kund

-0.71

fixed

-0.62

dating

-0.62

ership

-0.61

 Doctrine

-0.61

Mn

-0.59

 fund

-0.59

ãĥ´ãĤ¡

-0.58

doors

-0.58

POSITIVE LOGITS

udge

1.26

udging

1.22

umpy

1.22

iddles

1.06

aciously

1.04

iddle

1.03

ubby

1.03

iffin

1.01

aced

1.01

itt

0.99

Activations Density 0.022%

words related to dirtiness or degradation

occurrences of the prefix "gr," particularly in a context of describing negative traits or situations

No Comments

No Known Activations