INDEX

Explanations

text related to software or technology features

oai_token-act-pair · gpt-3.5-turbo

mentions of new or underlying features in technology-related contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

alg

-0.78

oner

-0.75

cffffcc

-0.74

sis

-0.73

externalActionCode

-0.73

Ń·

-0.71

uin

-0.67

abama

-0.66

kos

-0.66

thur

-0.66

POSITIVE LOGITS

ivity

0.89

iveness

0.85

 features

0.82

Feature

0.78

hered

0.77

afety

0.76

Features

0.76

 enhancements

0.75

 Features

0.71

ioned

0.71

Activations Density 0.035%

text related to software or technology features

mentions of new or underlying features in technology-related contexts

No Comments

No Known Activations