INDEX

Explanations

references to logging activities and related keywords in code and text

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

pet

-0.58

-0.52

 bare

-0.50

 level

-0.48

 point

-0.47

ר

-0.45

 pres

-0.44

fre

-0.44

 state

-0.43

 hard

-0.43

POSITIVE LOGITS

Personensuche

0.88

(!__

0.87

 HasFactory

0.85

afficheront

0.84

logger

0.83

MergeFrom

0.83

[]:

0.80

 betweenstory

0.80

 <=",

0.79

AccessorTable

0.79

Activations Density 0.139%

references to logging activities and related keywords in code and text

No Comments

No Known Activations