INDEX

Explanations

references to the speaker or self-identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_mlp_out

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

entibus

-0.76

 myſelf

-0.69

Efq

-0.69

IntoConstraints

-0.67

intenance

-0.66

 neceffary

-0.66

 poffible

-0.66

ziasztok

-0.66

dirkan

-0.65

 Longueur

-0.64

POSITIVE LOGITS

migrationBuilder

0.62

ineno

0.56

}),

0.55

es

0.55

&&\

0.54

0.53

erover

0.52

})));

0.52

ActionCreators

0.51

ً

0.51

Activations Density 0.017%

references to the speaker or self-identity

No Comments

No Known Activations