INDEX

Explanations

references to television and related media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

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

)$/,

-0.85

AndEndTag

-0.82

 Salta

-0.82

makeConstraints

-0.73

GeneratedValue

-0.73

nnnn

-0.72

]))

-0.71

}));

-0.70

}';

-0.70

DAP

-0.70

POSITIVE LOGITS

TV

1.47

 television

1.38

tv

1.24

TVs

1.22

 televisions

1.17

television

1.15

 Television

1.15

Tv

1.12

TV

1.08

Television

1.06

Activations Density 0.079%

references to television and related media

No Comments

No Known Activations