INDEX

Explanations

technical terms and metrics related to scientific and computational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

TypedDataSet

-0.82

 otomatig

-0.73

AsUp

-0.70

 ExecuteAsync

-0.66

InitVars

-0.61

 curé

-0.60

tagext

-0.59

 Buxton

-0.59

 Duque

-0.56

 Sandro

-0.56

POSITIVE LOGITS

 AssemblyVersion

0.63

ConverterFactory

0.58

ExtendWith

0.58

 StringTokenizer

0.56

󠁢

0.56

AttributedString

0.55

::::::::

0.54

:))

0.53

enschaft

0.53

…………………………………………

0.53

Activations Density 0.846%

technical terms and metrics related to scientific and computational contexts

No Comments

No Known Activations