INDEX

Explanations

generic programming terminology or structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

LookAnd

-0.73

 onAnimation

-0.60

 становника

-0.57

Aki

-0.57

 tartalomajánló

-0.56

 TextAppearance

-0.55

نگار

-0.54

twimg

-0.54

MessageTagHelper

-0.54

kib

-0.54

POSITIVE LOGITS

Generic

1.52

 Generic

1.03

generic

0.98

 generic

0.98

GENERIC

0.72

stdc

0.69

Personendaten

0.62

 EconPapers

0.61

 gener

0.59

 recensement

0.59

Activations Density 0.001%

generic programming terminology or structure

No Comments

No Known Activations