INDEX

Explanations

symbols and formatting indicators, suggesting a focus on code or structured data

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

 AssemblyCulture

-0.79

################

-0.70

AutoScale

-0.65

ThroughAttribute

-0.64

ünst

-0.64

Spoljašnje

-0.62

felde

-0.62

ABILITY

-0.62

chiat

-0.61

ortic

-0.61

POSITIVE LOGITS

ViewImports

0.98

✨:

0.76

enderror

0.69

 -----------

0.66

 françaises

0.66

HostException

0.64

 -------

0.63

 catholique

0.62

 ----------

0.62

 ---------

0.62

Activations Density 0.440%

symbols and formatting indicators, suggesting a focus on code or structured data

No Comments

No Known Activations