INDEX

Explanations

specific topics or elements within a larger text, such as errors, reports, examples, news, campaigns, or news conferences

oai_token-act-pair · gpt-3.5-turbo

references to specific cases or reports related to news articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

veland

-0.75

ategory

-0.64

ipe

-0.64

ãĤª

-0.64

ccording

-0.63

å§«

-0.62

pite

-0.61

é»Ĵ

-0.60

uilt

-0.60

chieve

-0.58

POSITIVE LOGITS

 incident

0.78

 debacle

0.78

 spree

0.71

 fiasco

0.71

Sov

0.68

 above

0.65

 revelations

0.65

Nib

0.65

 findings

0.65

 Tsarnaev

0.64

Activations Density 1.062%

specific topics or elements within a larger text, such as errors, reports, examples, news, campaigns, or news conferences

references to specific cases or reports related to news articles

No Comments

No Known Activations