INDEX

Explanations

numerical values such as measurements or percentages

oai_token-act-pair · gpt-3.5-turbo

numeric values and percentages associated with data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

-0.56

 leveled

-0.53

 tremend

-0.53

 liner

-0.52

omorphic

-0.51

 therm

-0.50

nsic

-0.50

ements

-0.50

 censor

-0.48

urion

-0.48

POSITIVE LOGITS

<|endoftext|>

0.91

 ********************************

0.89

 =================================================================

0.84

 ----------------

0.78

 =====

0.75

 =================

0.75

 --------------------

0.75

 --------------------------------

0.74

};

0.71

 Miscellaneous

0.70

Activations Density 0.270%

numerical values such as measurements or percentages

numeric values and percentages associated with data

No Comments

No Known Activations