INDEX

Explanations

programming and technical terminology related to functions and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

AccessorTable

-0.97

enumi

-0.95

ViewFeatures

-0.91

StoryboardSegue

-0.85

setVerticalGroup

-0.78

LookAnd

-0.74

 AssemblyProduct

-0.70

enumii

-0.67

Sucesor

-0.66

 Réponses

-0.66

POSITIVE LOGITS

 optional

0.98

optional

0.86

 Optional

0.84

OPTIONAL

0.81

 must

0.81

Optional

0.78

 OPTIONAL

0.77

 opcional

0.74

 specifies

0.72

opcional

0.70

Activations Density 0.430%

programming and technical terminology related to functions and parameters

No Comments

No Known Activations