INDEX

Explanations

technical terms and constructs related to coding and data processing

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

HostException

-0.81

JSONException

-0.80

URLException

-0.78

 HttpHeaders

-0.71

+#+#

-0.70

TargetException

-0.70

CodedInputStream

-0.69

ActionEvent

-0.67

 DbSet

-0.66

ItemBackground

-0.65

POSITIVE LOGITS

Default

0.76

 Default

0.71

 default

0.61

 Simple

0.60

Simple

0.60

default

0.57

 تضيفلها

0.57

simple

0.54

DefaultValue

0.54

 désolés

0.53

Activations Density 0.264%

technical terms and constructs related to coding and data processing

No Comments

No Known Activations