INDEX

Explanations

references to food-related categories and their connections in context

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

Follows the word "and"

np_acts-logits-general · gemini-2.0-flash

and followed by categories

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

...

-0.48

}}}}

-0.48

the

-0.47

--

-0.47

</i>

-0.46

med

-0.45

 Group

-0.45

 King

-0.44

li

-0.44

POSITIVE LOGITS

 pleaſure

0.88

 Jefus

0.84

 GenerationType

0.83

 Monfieur

0.79

 ſche

0.77

 raiſ

0.76

 auffi

0.72

endphp

0.71

IntoConstraints

0.71

 myſelf

0.71

Activations Density 0.427%

references to food-related categories and their connections in context

Follows the word "and"

and followed by categories

No Comments

No Known Activations