INDEX

Explanations

references to specific individuals or characters

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-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

enumi

-0.83

StoryboardSegue

-0.78

########.

-0.73

OrNil

-0.72

ImageContext

-0.71

BrowserModule

-0.71

AccessorTable

-0.70

mergeFrom

-0.69

AutoresizingMask

-0.69

ngdoc

-0.68

POSITIVE LOGITS

 knights

0.95

 Knight

0.94

 knight

0.92

Knight

0.86

 Knights

0.83

hover

0.81

 KNIGHT

0.77

knight

0.72

 bullied

0.72

 clouds

0.71

Activations Density 0.104%

references to specific individuals or characters

No Comments

No Known Activations