INDEX

Explanations

phrases indicating the act of highlighting or emphasizing information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ftagPool

-0.82

 समीक्षाएं

-0.63

ServiceModel

-0.60

IContainer

-0.58

principalTable

-0.58

wahati

-0.55

SourceChecksum

-0.55

úgó

-0.55

évaluateur

-0.55

 GenerationType

-0.54

POSITIVE LOGITS

 fingers

0.80

 specifically

0.67

 doigt

0.66

 finger

0.64

 toward

0.59

 attention

0.58

fingers

0.58

 accusing

0.58

ly

0.57

 towards

0.56

Activations Density 0.190%

phrases indicating the act of highlighting or emphasizing information

No Comments

No Known Activations