INDEX

Explanations

numerical figures and percentages

oai_token-act-pair · gpt-3.5-turbo

references to polling percentages and statistical comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

pire

-0.62

æ©

-0.61

acus

-0.60

 compass

-0.60

rouse

-0.60

-0.58

 exce

-0.57

ettings

-0.57

ãĥ¯ãĥ³

-0.56

airo

-0.56

POSITIVE LOGITS

1.54

1.53

1.52

1.49

1.47

1.45

1.44

Activations Density 0.201%

numerical figures and percentages

references to polling percentages and statistical comparisons

No Comments

No Known Activations