INDEX

Explanations

syntactical structures and formatting in code or structured text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

IsMutable

-0.47

 […]

-0.43

nas

-0.43

ing

-0.42

umur

-0.42

랜

-0.40

__((

-0.40

ﬂ

-0.40

Hyp

-0.40

↵

-0.39

POSITIVE LOGITS

+#+

1.01

queryInterface

0.89

 CreateTagHelper

0.88

GEBURTSDATUM

0.82

 ModelExpression

0.77

 سكانية

0.73

évaluateur

0.72

ConstraintMaker

0.71

 AssemblyCulture

0.69

 AssemblyVersion

0.69

Activations Density 0.639%

syntactical structures and formatting in code or structured text

No Comments

No Known Activations