INDEX

Explanations

mentions of a small group of items or individuals

oai_token-act-pair · gpt-3.5-turbo

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

 causation

-0.59

 unfocusedRange

-0.59

 anticipation

-0.57

iola

-0.56

 Conversation

-0.54

Recomm

-0.53

 assigning

-0.52

 relativity

-0.51

 appraisal

-0.50

abad

-0.49

POSITIVE LOGITS

of

1.04

eenth

0.96

 thereof

0.87

 dozen

0.85

Of

0.80

dozen

0.78

atical

0.75

 thousand

0.75

een

0.74

 hundred

0.73

Activations Density 0.041%

mentions of a small group of items or individuals

No Comments

No Known Activations