INDEX

Explanations

technical terms and references related to objects, configurations, and documentation in programming and engineering contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ized

-0.72

izing

-0.70



-0.65

extAlignment

-0.64

Bibliograf

-0.62

IZED

-0.62

izer

-0.62

entiel

-0.62

IZER

-0.61

brainly

-0.61

POSITIVE LOGITS

 sulph

0.74

 himſelf

0.69

AddTagHelper

0.69

.,

0.68

Eqs

0.68

 Pollut

0.66

 mags

0.66

 refs

0.66

eqn

0.65

 celebs

0.65

Activations Density 1.157%

technical terms and references related to objects, configurations, and documentation in programming and engineering contexts

No Comments

No Known Activations