INDEX

Explanations

references to alternative options, variables, or evidence in a context that suggests comparison or differentiation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 defaultstate

-0.77

первых

-0.76

 كومونز

-0.74

はじめに

-0.72

cillor

-0.63

 chi̍t

-0.63

 gyhoeddwyd

-0.61

tymologie

-0.60

ArrayOf

-0.60

ỡng

-0.60

POSITIVE LOGITS

 than

0.84

 kuin

0.66

Another

0.61

Other

0.61

 similarly

0.60

 Another

0.59

 outros

0.59

 Other

0.56

Others

0.55

cier

0.55

Activations Density 0.607%

references to alternative options, variables, or evidence in a context that suggests comparison or differentiation

No Comments

No Known Activations