INDEX

Explanations

references to membranes in various contexts, particularly in biological and chemical studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Goldsmith

-0.72

allery

-0.72

募

-0.72

casian

-0.71

KURZBESCHREIBUNG

-0.71

 Dryden

-0.69

 Aitken

-0.69

CrossRef

-0.68

nsw

-0.66

Cik

-0.66

POSITIVE LOGITS

 للمعارف

0.88

affili

0.86

 שוליים

0.86

 Mandate

0.82

▬

0.79

omitempty

0.76

Personnel

0.75

mstyle

0.74

írus

0.73

SDL

0.73

Activations Density 0.081%

references to membranes in various contexts, particularly in biological and chemical studies

No Comments

No Known Activations