INDEX

Explanations

terms and phrases related to definitions and specifications in technical contexts

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

Theorem

-0.56

okovic

-0.52

czyny

-0.52

 souten

-0.51

 béné

-0.51

 namanya

-0.50

temon

-0.49

ibouti

-0.49

TextAppearance

-0.48

 principles

-0.48

POSITIVE LOGITS

 referring

0.92

 connotations

0.84

 synonymous

0.82

 connotation

0.77

 applied

0.76

 misused

0.76

 interchangeable

0.75

 synonym

0.75

WriteAttribute

0.73

 used

0.73

Activations Density 0.433%

terms and phrases related to definitions and specifications in technical contexts

No Comments

No Known Activations