INDEX

Explanations

specific names or labels in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

位

-0.64

 Bourgoin

-0.60

 harian

-0.59

❷

-0.58

望

-0.55

 ovan

-0.54

en

-0.54

Station

-0.54

newArray

-0.54

POSITIVE LOGITS

 Coss

0.96

Azz

0.96

Utt

0.89

MethodManager

0.89

CrossRef

0.87

 Hatt

0.86

 Genn

0.86

edd

0.83

 Hipp

0.83

 Monfieur

0.82

Activations Density 0.945%

specific names or labels in scientific or technical contexts

No Comments

No Known Activations