INDEX

Explanations

references to statistical values or results in a study

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_mlp_out

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

-1.67

-1.66

-1.63

-1.61

if

-1.59

 ſche

-1.57

-1.56

POSITIVE LOGITS

ratulations

1.98

—

1.84

BibitemShut

1.72

Amicalement

1.72

NUMX

1.66

%\]

1.62

gorithm

1.59

iffance

1.58

esterday

1.57

ficulty

1.56

Activations Density 0.208%

references to statistical values or results in a study

No Comments

No Known Activations