INDEX

Explanations

numerical values associated with data, such as years or parameter numbers

oai_token-act-pair · gpt-3.5-turbo

various formatting marks or end-of-text indicators

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

gha

-0.63

 vulner

-0.58

 Channel

-0.57

 explan

-0.56

cair

-0.53

accompan

-0.53

 shenan

-0.53

 Instr

-0.52

 Dollars

-0.52

ecause

-0.52

POSITIVE LOGITS

/-

0.66

\":

0.65

ventus

0.64

imil

0.63

mosp

0.62

esity

0.61

FactoryReloaded

0.60

":{"

0.60

lement

0.60

tenance

0.58

Activations Density 0.077%

numerical values associated with data, such as years or parameter numbers

various formatting marks or end-of-text indicators

No Comments

No Known Activations