INDEX

Explanations

numerical values and identifiers related to data or specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Rosie

-0.87

 Rosen

-0.77

Rosie

-0.73

Heb

-0.71

 Moray

-0.71

 Bever

-0.69

 Jimin

-0.66

 Doherty

-0.66

 Kras

-0.65

 Garza

-0.65

POSITIVE LOGITS

 Jones

0.96

Jones

0.88

 Simmons

0.83

 Bong

0.77

 Marlow

0.77

 jones

0.75

jones

0.75

Bong

0.74

 Dreyfus

0.74

 Kamb

0.74

Activations Density 1.668%

numerical values and identifiers related to data or specifications

No Comments

No Known Activations