INDEX

Explanations

personal pronouns referring to actions or consequences

oai_token-act-pair · gpt-3.5-turbo

instances of the pronoun "it."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IDA

-0.65

 Eighth

-0.63

Jaw

-0.62

IX

-0.57

 Chair

-0.57

Missing

-0.56

Statement

-0.56

oided

-0.55

Major

-0.55

 Reporting

-0.54

POSITIVE LOGITS

 tends

1.42

 becomes

1.40

 varies

1.39

 happens

1.36

 depends

1.33

 occurs

1.32

 boils

1.31

 slows

1.29

 affects

1.28

 takes

1.27

Activations Density 0.208%

personal pronouns referring to actions or consequences

instances of the pronoun "it."

No Comments

No Known Activations