INDEX

Explanations

phrases indicating actions or commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

rungsseite

-0.83

SourceChecksum

-0.67

GroupLayout

-0.65

Merkmale

-0.61

oa̍t

-0.60

vise

-0.60

 &___

-0.59

ConstraintMaker

-0.56

runOnUiThread

-0.56

vstack

-0.56

POSITIVE LOGITS

 FetchType

0.70

zzleHttp

0.64

UIControlState

0.64

 MainAxisSize

0.59

lk

0.55

 Antif

0.55

 дописавши

0.55

 claws

0.55

 Beacon

0.54

abetta

0.54

Activations Density 0.040%

phrases indicating actions or commands

No Comments

No Known Activations