INDEX

Explanations

references or citations within a text

oai_token-act-pair · gpt-3.5-turbo

references to citations or sources used in arguments

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

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

ensibly

-0.77

cos

-0.75

Sphere

-0.71

byss

-0.69

mire

-0.69

ateurs

-0.68

icion

-0.67

mid

-0.66

encia

-0.66

quer

-0.65

POSITIVE LOGITS

 similarities

0.95

 preced

0.95

 accomplishments

0.93

 debunked

0.90

 example

0.87

 similarity

0.85

 precedent

0.85

 examples

0.84

 shortcomings

0.83

 inaccur

0.83

Activations Density 0.324%

references or citations within a text

references to citations or sources used in arguments

No Comments

No Known Activations