INDEX

Explanations

instances of citations or references to external information

oai_token-act-pair · gpt-3.5-turbo

instances of the word "cite" and its variations, indicating references or citations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

quer

-0.90

soever

-0.82

ttle

-0.78

cos

-0.77

emort

-0.74

erer

-0.74

isode

-0.73

 teasp

-0.72

peat

-0.72

spawn

-0.72

POSITIVE LOGITS

 examples

1.15

 similarities

1.01

 anecdotes

1.00

 preced

0.97

 inconsistencies

0.96

 unnamed

0.94

 statistics

0.94

 anecdotal

0.94

 studies

0.93

 passages

0.89

Activations Density 0.111%

instances of citations or references to external information

instances of the word "cite" and its variations, indicating references or citations in the text

No Comments

No Known Activations