INDEX

Explanations

references to the column structure of data tables and related terms in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 userSchema

-0.59

crt

-0.58

fossil

-0.58

 Unburied

-0.57

autique

-0.57

 additionally

-0.57

AGED

-0.55

 Martyn

-0.54

BAI

-0.53

 Jaffe

-0.53

POSITIVE LOGITS

mus

0.92

AddHtmlAttribute

0.83

col

0.76

Mus

0.74

mus

0.70

Mus

0.69

 Breaking

0.68

Breaking

0.67

breaking

0.67

 fusca

0.67

Activations Density 0.042%

references to the column structure of data tables and related terms in text

No Comments

No Known Activations