INDEX

Explanations

various programming constructs and annotations related to class definitions and database configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

InputTagHelper

-0.83

PostInfinity

-0.70

وأضاف

-0.69

日閲覧

-0.68

BufferException

-0.67

LookAnd

-0.66

:+:

-0.66

erun

-0.65

onView

-0.64

 Bulletin

-0.62

POSITIVE LOGITS

public

0.81

private

0.72

expandindo

0.61

ⓧ

0.55

↵↵

0.54

 Audiodateien

0.54

irnov

0.53

 récents

0.53

pr

0.52

addGap

0.52

Activations Density 0.060%

various programming constructs and annotations related to class definitions and database configurations

No Comments

No Known Activations