INDEX

Explanations

words or symbols associated with data or numeric values

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

-0.53

–

-0.49

in

-0.46

rodu

-0.46

 must

-0.45

May

-0.45

-0.44

tim

-0.43

da

-0.43

Len

-0.42

POSITIVE LOGITS

FormTagHelper

0.87

rungsseite

0.86

 myſelf

0.82

WithIOException

0.80

Hentet

0.80

 auffi

0.77

DockStyle

0.77

NUMX

0.75

IntoConstraints

0.74

WebVitals

0.74

Activations Density 0.934%

words or symbols associated with data or numeric values

No Comments

No Known Activations