INDEX

Explanations

code snippets or function definitions related to standardization and validation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

TintMode

-0.65

WebControls

-0.57

oredCriteria

-0.51

]=>

-0.48

ValueGeneration

-0.47

igshid

-0.47

Carcinogenicity

-0.46

metology

-0.46

Po

-0.46

Bar

-0.44

POSITIVE LOGITS

tagHelperRunner

0.84

InjectAttribute

0.81

ConstraintMaker

0.79

matchCondition

0.79

NameInMap

0.77

AddTagHelper

0.73

Personendaten

0.72

 CreateTagHelper

0.72

 EconPapers

0.72

twimg

0.72

Activations Density 0.511%

code snippets or function definitions related to standardization and validation processes

No Comments

No Known Activations