INDEX

Explanations

requests for help or assistance

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 herself

-0.64

IsMutable

-0.61

 itself

-0.51

 often

-0.50

itself

-0.47

often

-0.47

styleable

-0.46

herself

-0.45

сшта

-0.45

Вам

-0.44

POSITIVE LOGITS

COUVER

0.65

contentLoaded

0.65



0.62

Revenir

0.62

 help

0.56

 consultato

0.56

rieben

0.56

WriteLiteral

0.56

دانشنامهٔ

0.55

Explicación

0.54

Activations Density 0.165%

requests for help or assistance

No Comments

No Known Activations