INDEX

Explanations

various ways or methods

oai_token-act-pair · gpt-3.5-turbo

phrases related to methods or approaches

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

ulus

-0.71

uster

-0.70

IFIED

-0.70

ieu

-0.69

usters

-0.69

Ä±

-0.65

 XIII

-0.65

inately

-0.64

anche

-0.64

-0.63

POSITIVE LOGITS

finding

1.02

 ways

0.84

pointers

0.81

 Ways

0.80

eries

0.79

cale

0.78

styles

0.76

etting

0.73

hell

0.73

hooting

0.70

Activations Density 0.029%

various ways or methods

phrases related to methods or approaches

No Comments

No Known Activations