INDEX

Explanations

words related to technical instructions or programming

oai_token-act-pair · gpt-3.5-turbo

phrases related to scenarios and conditions 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Negro

-0.71

 Philippine

-0.66

 Kazakh

-0.65

 rumours

-0.65

 Zionist

-0.65

 witnessed

-0.65

 Bulgarian

-0.64

 Chilean

-0.64

 Ulster

-0.63

 Israeli

-0.62

POSITIVE LOGITS

uitive

0.82

pmwiki

0.78

itiz

0.74

 maximizing

0.74

—"

0.73

you

0.72

you

0.72

Your

0.72

 iter

0.71

your

0.71

Activations Density 0.583%

words related to technical instructions or programming

phrases related to scenarios and conditions in various contexts

No Comments

No Known Activations