INDEX

Explanations

nouns related to individual items or entities within a larger group or system

oai_token-act-pair · gpt-3.5-turbo

terms related to individual components or entities within a larger system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

dylib

-0.66

aukee

-0.64

 Newsletter

-0.61

 Things

-0.61

DERR

-0.55

 Balls

-0.55

bows

-0.53

 arteries

-0.53

Cla

-0.52

 Laur

-0.52

POSITIVE LOGITS

 individually

1.29

 separately

0.98

 except

0.91

 imaginable

0.78

 independently

0.78

 contributes

0.77

 corresponds

0.75

 vying

0.69

ieth

0.68

 thereafter

0.67

Activations Density 0.125%

nouns related to individual items or entities within a larger group or system

terms related to individual components or entities within a larger system

No Comments

No Known Activations