INDEX

Explanations

phrases related to authorizations or permissions

oai_token-act-pair · gpt-3.5-turbo

demonstrative pronouns and phrases indicating specific subjects or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

lining

-0.76

 ********************************

-0.66

alties

-0.65

CVE

-0.64

));

-0.62

izo

-0.59

ielding

-0.57

 Huckabee

-0.56

ginx

-0.56

)).

-0.56

POSITIVE LOGITS

''

0.76

.""

0.72

[/

0.72

"],

0.71

"—

0.70

Â»

0.67

É

0.67

estine

0.66

cellence

0.66

%"

0.66

Activations Density 0.191%

phrases related to authorizations or permissions

demonstrative pronouns and phrases indicating specific subjects or ideas

No Comments

No Known Activations