INDEX

Explanations

code-related terms and structural elements often found in programming or documentation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ówczas

-0.69

ModelSerializer

-0.69

Архівовано

-0.68

)";

-0.65

hdashline

-0.65

‬‬

-0.65

XtraEditors

-0.65

 оригіналу

-0.64

)");

-0.62

)"),

-0.61

POSITIVE LOGITS

 possib

0.47

 postIndex

0.46

0.45

fal

0.43

hil

0.43

 nahilalakip

0.43

vet

0.42

ly

0.41

露

0.41

eld

0.41

Activations Density 0.655%

code-related terms and structural elements often found in programming or documentation

No Comments

No Known Activations