INDEX

Explanations

references to specific rows in a dataset or table

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

NewUrlParser

-0.87

 AssemblyCulture

-0.82

Память

-0.75

 isolé

-0.67

 religieuses

-0.67

-0.66

 corner

-0.65

 blessés

-0.65

pyplot

-0.64

 Ahnung

-0.64

POSITIVE LOGITS

Row

0.92

Row

0.86

vessel

0.56

ski

0.55

 /\.(

0.54

RegressionTest

0.53

 municipality

0.53

municip

0.52

 vessel

0.51

intenant

0.50

Activations Density 0.041%

references to specific rows in a dataset or table

No Comments

No Known Activations