INDEX

Explanations

phrases indicating justification or reasoning, especially in legal or procedural contexts

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

XtraGrid

-0.60

zzleHttp

-0.57

 defaultstate

-0.56

 AssemblyVersion

-0.55

rokken

-0.55

yntaxException

-0.53

contentLoaded

-0.51

 Administrativna

-0.51

anyahu

-0.50

omials

-0.50

POSITIVE LOGITS

+:+

0.70

 Waarom

0.58

 Emits

0.57

ływ

0.54

 WARRANT

0.54

 للمعارف

0.53

 épaules

0.53

为什么要

0.51

円

0.51

 solch

0.49

Activations Density 0.583%

phrases indicating justification or reasoning, especially in legal or procedural contexts

No Comments

No Known Activations