INDEX

Explanations

numerical values or data points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

↵↵

-0.83

 defaultstate

-0.68

↵↵↵

-0.67

principalColumn

-0.62

 dipende

-0.59

#+#

-0.59

 HasFactory

-0.56

 industriale

-0.56

↵

-0.56

POSITIVE LOGITS

0.69

0.68

0.65

archiviato

0.64

WriteAttribute

0.63

Activations Density 0.047%

numerical values or data points

No Comments

No Known Activations