INDEX

Explanations

words related to significant impact or importance

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "role" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Eyes

-0.61

affles

-0.59

 Junk

-0.59

hound

-0.58

ocaust

-0.57

trap

-0.57

apest

-0.55

 Flesh

-0.55

urses

-0.55

Results

-0.54

POSITIVE LOGITS

playing

0.95

in

0.95

 therein

0.94

 role

0.87

 facilitating

0.81

 roles

0.80

role

0.79

 overseeing

0.78

 helping

0.75

 influencing

0.75

Activations Density 0.061%

words related to significant impact or importance

references to the concept of "role" in various contexts

No Comments

No Known Activations