INDEX

Explanations

descriptions of impressive physical feats or performances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

loven

-0.46

quiler

-0.45

 يتيمه

-0.42

看不

-0.41

 comisiones

-0.40

 accedi

-0.40

MPa

-0.40

 zgod

-0.40

 coscienza

-0.39

ApiModelProperty

-0.39

POSITIVE LOGITS

 Walkover

0.83

 jump

0.78

 reverse

0.74

 leap

0.73

 jumps

0.73

 flip

0.71

MigrationBuilder

0.71

 inverted

0.70

原地

0.69

 Reverse

0.69

Activations Density 0.263%

descriptions of impressive physical feats or performances

No Comments

No Known Activations