INDEX

Explanations

expressions related to future plans or hypothetical scenarios

oai_token-act-pair · gpt-3.5-turbo

phrases that express conditions or scenarios where certain conditions need to be met

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

ONT

-0.74

Ô

-0.70

\">

-0.67

ãģ®ç

-0.67

"]=>

-0.66

EStreamFrame

-0.66

ãĤ§

-0.64

âĸĳâĸĳ

-0.64

ilib

-0.64

enegger

-0.63

POSITIVE LOGITS

 weren

0.77

 survives

0.75

 succeeds

0.75

 someday

0.74

mist

0.73

 slightest

0.71

 fails

0.69

 persists

0.68

 ever

0.67

 were

0.66

Activations Density 0.204%

expressions related to future plans or hypothetical scenarios

phrases that express conditions or scenarios where certain conditions need to be met

No Comments

No Known Activations