INDEX

Explanations

references to inner and outer components or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

raborty

-0.84

ModelAdmin

-0.77

 Loeb

-0.76

gerald

-0.75

 Gibbons

-0.75

ViewFeatures

-0.73

hassee

-0.73

chließend

-0.72

WriteLiteral

-0.72

smöglichkeiten

-0.72

POSITIVE LOGITS

 INNER

0.90

 Inner

0.89

innerWidth

0.85

 inner

0.85

inner

0.82

Inner

0.79

er

0.73

INNER

0.71

ner

0.70

__[

0.69

Activations Density 0.119%

references to inner and outer components or structures

No Comments

No Known Activations