INDEX

Explanations

instances of the verb "see" and its variations indicating observation or perception

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 loisirs

-0.78

 lunghi

-0.78

 universitarios

-0.75

knapp

-0.74

Grath

-0.74

unately

-0.74

Kort

-0.72

 procé

-0.70

 Hofmann

-0.69

 Kaufman

-0.69

POSITIVE LOGITS

 sees

1.79

 Sees

1.78

see

1.74

SEE

1.62

See

1.62

 seen

1.59

saw

1.59

See

1.57

see

1.52

 seeing

1.48

Activations Density 0.134%

instances of the verb "see" and its variations indicating observation or perception

No Comments

No Known Activations