INDEX

Explanations

terms related to algebraic topology and mirror symmetry in mathematical contexts

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

 africaine

-0.69

 middag

-0.63

 avoient

-0.60

 auroit

-0.59

 interessi

-0.57

dorfer

-0.57

 étoit

-0.57

 rosse

-0.57

 auffi

-0.56

 plufieurs

-0.56

POSITIVE LOGITS

Tor

0.82

belt

0.79

tor

0.74

tor

0.72

Tor

0.70

kers

0.69

 belt

0.64

ANTLR

0.61

 Belt

0.59

TOR

0.59

Activations Density 2.056%

terms related to algebraic topology and mirror symmetry in mathematical contexts

No Comments

No Known Activations