INDEX

Explanations

the word 'idd' with various numerical activations, seemingly focusing on different contexts or uses of this specific term

oai_token-act-pair · gpt-3.5-turbo

instances of the term "Yiddish."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

pora

-0.72

 metast

-0.69

ãĥīãĥ©ãĤ´ãĥ³

-0.65

OPLE

-0.65

 convergence

-0.61

URRENT

-0.60

 AUTHOR

-0.60

economic

-0.59

Aux

-0.59

 Canaver

-0.59

POSITIVE LOGITS

ety

0.95

ski

0.95

eret

0.89

eenth

0.88

olesc

0.88

lesh

0.88

0.87

itional

0.87

olph

0.83

emouth

0.82

Activations Density 0.024%

the word 'idd' with various numerical activations, seemingly focusing on different contexts or uses of this specific term

instances of the term "Yiddish."

No Comments

No Known Activations