INDEX

Explanations

elements and structured concepts such as steps, principles, or models related to professional guidelines or instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

InitVars

-0.58

 negociaciones

-0.46

nyttet

-0.46

makeText

-0.45

harapkan

-0.45

setUp

-0.44

ToLoad

-0.44

chnet

-0.44

who

-0.44

aarrggbb

-0.43

POSITIVE LOGITS

LookAnd

0.72

 Lordship

0.62

 acronym

0.61

клопе

0.61

FOG

0.61

ConverterFactory

0.60

 Llor

0.60

CloseOperation

0.59

Istorija

0.58

 Conch

0.57

Activations Density 0.309%

elements and structured concepts such as steps, principles, or models related to professional guidelines or instructions

No Comments

No Known Activations