INDEX

Explanations

sections or codes that indicate the start of a new segment or a new idea in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

AsUp

-0.82

aarrggbb

-0.76

 betweenstory

-0.73

 <=",

-0.70

:✨

-0.68

 unknownFields

-0.68

ArrowToggle

-0.67

 tartalomajánló

-0.66

RegressionTest

-0.64

memoized

-0.61

POSITIVE LOGITS

 للمعارف

1.00

 Wicidata

0.86

CodeAttribute

0.81

 تانيه

0.78

Tikang

0.77

 يتيمه

0.77

ScopeManager

0.76

 BoxDecoration

0.71

ագրություններ

0.69

Архівовано

0.69

Activations Density 0.038%

sections or codes that indicate the start of a new segment or a new idea in a structured format

No Comments

No Known Activations