INDEX

Explanations

terms related to fixed or rigid structures and parameters

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 <<<<<<<<<<<<<<

-0.80

 EconPapers

-0.69

enumi

-0.68

migrationBuilder

-0.66

DoubleQuotes

-0.66

samt

-0.65

opr

-0.65

UrlResolution

-0.64

esez

-0.64

']>;

-0.59

POSITIVE LOGITS

 fixed

1.00

Fixed

0.91

fixed

0.91

 Fixed

0.89

 FIXED

0.87

FIXED

0.86

 fixe

0.78

 固定

0.74

固定

0.73

fix

0.73

Activations Density 0.708%

terms related to fixed or rigid structures and parameters

No Comments

No Known Activations