INDEX

Explanations

instances of people being observed or spotted

oai_token-act-pair · gpt-3.5-turbo

instances of the word "seen" 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 @ 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

iets

-0.71

idity

-0.71

angan

-0.65

 sclerosis

-0.64

aceutical

-0.63

 misunderstanding

-0.62

 antidepressants

-0.59

RET

-0.59

mental

-0.59

forestation

-0.58

POSITIVE LOGITS

seeing

0.74

swick

0.74

ById

0.74

 photograp

0.73

dust

0.73

agascar

0.73

 hovering

0.71

lifting

0.68

ãĤĬ

0.68

 alive

0.67

Activations Density 0.056%

instances of people being observed or spotted

instances of the word "seen" in various contexts

No Comments

No Known Activations