INDEX

Explanations

terms related to binary code or systems in written texts

oai_token-act-pair · gpt-3.5-turbo

terms related to binary systems and executable files

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Interstitial

-0.81

uay

-0.81

ulz

-0.79

urers

-0.78

ieri

-0.78

rir

-0.77

armac

-0.76

IGH

-0.76

ugu

-0.73

ndra

-0.72

POSITIVE LOGITS

 blob

0.94

 Laden

0.80

omial

0.78

binary

0.71

 binary

0.68

ãĥĥãĥī

0.68

dayName

0.65

agonal

0.65

 Binary

0.65

 coded

0.64

Activations Density 0.014%

terms related to binary code or systems in written texts

terms related to binary systems and executable files

No Comments

No Known Activations