INDEX

Explanations

references and definitions in code or data formatting

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LookAnd

-0.67

aroni

-0.61

Spoljašnje

-0.61

 SEDS

-0.60

("}");

-0.60

 oprot

-0.59

 ""],

-0.58

"])

-0.58

----</

-0.58

ьаж

-0.57

POSITIVE LOGITS

0.67

 AssemblyTitle

0.66

 ICollection

0.60

InlineData

0.59

ⓘ

0.57

seamnă

0.57

 مواليد

0.57

 therein

0.56

writerow

0.53

 iyon

0.53

Activations Density 0.562%

references and definitions in code or data formatting

No Comments

No Known Activations