INDEX

Explanations

code-related structures and function definitions, especially in programming languages or environments that use specific decorators and annotations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LookAnd

-0.74

 BoxFit

-0.70

 propOrder

-0.68

 архивлан

-0.58

Hentet

-0.56

 Majefty

-0.56

Biggest

-0.56

__(/*!

-0.56

 isNameExpr

-0.55

enoord

-0.55

POSITIVE LOGITS

Ast

0.64

 Sack

0.62

^{(

0.60

FormTagHelper

0.58

Ast

0.57

ato

0.56

dub

0.55

 Atoms

0.54

 atoms

0.53

 Apre

0.53

Activations Density 2.819%

code-related structures and function definitions, especially in programming languages or environments that use specific decorators and annotations

No Comments

No Known Activations