INDEX

Explanations

references to origins or sources within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

TintMode

-0.71

 onPostExecute

-0.61

dessus

-0.54

InjectAttribute

-0.53

focusable

-0.53

expandindo

-0.52

 فريبيس

-0.52

 réessayer

-0.52

EDEFAULT

-0.52

сшта

-0.52

POSITIVE LOGITS

 scratch

0.80



0.66

Scratch

0.64

scratch

0.62

 Scratch

0.61

Xna

0.57

 doInBackground

0.55

#+#

0.54

FieldNumber

0.54

Bronnen

0.54

Activations Density 0.116%

references to origins or sources within the text

No Comments

No Known Activations