INDEX

Explanations

phrases related to certainty and approximation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating probability or likelihood

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

åĤ

-0.68

è¦ļéĨĴ

-0.66

ocratic

-0.64

Ö

-0.64

umbn

-0.63

taboola

-0.63

ensis

-0.62

clud

-0.61

pent

-0.61

èĢ

-0.59

POSITIVE LOGITS

entimes

0.82

 Helpful

0.81

 Leader

0.79

 importantly

0.79

Sounds

0.73

resa

0.71

 Enough

0.70

olate

0.70

itionally

0.69

inct

0.69

Activations Density 0.105%

phrases related to certainty and approximation

phrases indicating probability or likelihood

No Comments

No Known Activations