INDEX

Explanations

references to amplifiers or amplification-related terms

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

ConstraintMaker

-0.70

发表于

-0.67

 незавершена

-0.65

'])){

-0.65

 MessageBoxIcon

-0.64

'},

-0.64

findpost

-0.62

Rhestr

-0.62

Portail

-0.60

tvguidetime

-0.60

POSITIVE LOGITS

 Pairing

0.80

 merge

0.78

merge

0.76

 Merge

0.75

 pairing

0.75

amp

0.73

Merge

0.73

 consensus

0.72

 merged

0.70

 pairings

0.69

Activations Density 0.106%

references to amplifiers or amplification-related terms

No Comments

No Known Activations