INDEX

Explanations

quantitative data and numerical references within academic literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AutoScaleMode

-0.99

GraphicsUnit

-0.84

aarrggbb

-0.82

featureID

-0.81

Autoritní

-0.81

TagMode

-0.80

SourceChecksum

-0.80

 '\\;'

-0.77

 AssemblyVersion

-0.75

 betale

-0.74

POSITIVE LOGITS

gernaut

0.55

 analis

0.46

unhofer

0.43

liar

0.43

 analys

0.42

ране

0.42

 analysis

0.42

Var

0.42

Comp

0.40

Activations Density 0.179%

quantitative data and numerical references within academic literature

No Comments

No Known Activations