INDEX

Explanations

technical terms related to statistical analysis and data examination typically used in research contexts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

migrationBuilder

-0.73

stdc

-0.66

GraphicsUnit

-0.60

mme

-0.54

point

-0.53

 continúas

-0.52

 point

-0.51

PerformLayout

-0.50

enumi

-0.49

tease

-0.49

POSITIVE LOGITS

FormTagHelper

0.57

 sandero

0.56

 glove

0.54

assertIn

0.53

 moat

0.52

ropoda

0.51

 propOrder

0.51

 muita

0.50

AnchorStyles

0.50

 ComVisible

0.50

Activations Density 0.030%

technical terms related to statistical analysis and data examination typically used in research contexts

No Comments

No Known Activations