INDEX

Explanations

terms related to components or parts in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to "components" 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

standing

-0.73

scrib

-0.72

 Croat

-0.71

kers

-0.69

berman

-0.68

grim

-0.68

fm

-0.68

sle

-0.68

geons

-0.68

 Limbaugh

-0.66

POSITIVE LOGITS

 thereof

0.99

 components

0.94

 component

0.90

 Components

0.88

 subsystem

0.88

 Component

0.87

 parts

0.85

als

0.83

ivity

0.77

 supplier

0.76

Activations Density 0.036%

terms related to components or parts in various contexts

references to "components" in various contexts

No Comments

No Known Activations