INDEX

Explanations

numerical codes or sequences in a specific format

oai_token-act-pair · gpt-3.5-turbo

numerical values and data points, primarily in a structured format

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ulet

-0.78

 tremend

-0.70

udeb

-0.68

pse

-0.65

 endors

-0.64

ween

-0.64

Afee

-0.63

sole

-0.60

ado

-0.60

 forecast

-0.59

POSITIVE LOGITS

Interstitial

0.96

ACTED

0.81

NetMessage

0.70

<+

0.68

lam

0.68

<@

0.66

PM

0.64

inka

0.64

:{

0.62

AMS

0.62

Activations Density 0.056%

numerical codes or sequences in a specific format

numerical values and data points, primarily in a structured format

No Comments

No Known Activations