INDEX

Explanations

fragments of code or programming-related syntax, specifically within a structured or formatted context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Cor

-0.46

ctional

-0.43

tiglie

-0.42

Pro

-0.42

szön

-0.42

-0.41

pro

-0.40

in

-0.40

actylus

-0.39

’

-0.39

POSITIVE LOGITS

 ModelExpression

0.92

aarrggbb

0.90

évaluateur

0.83

expandindo

0.81

GEBURTS

0.78

kháu

0.74

RetentionPolicy

0.72

WriteTagHelper

0.72

 للمعارف

0.71

qrstuvwxyz

0.71

Activations Density 0.939%

fragments of code or programming-related syntax, specifically within a structured or formatted context

No Comments

No Known Activations