INDEX

Explanations

references to statistical or experimental data and comparisons

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

Technical terminology, units, or named variants in formal/academic documents, often preceding punctuation or appearing in specific contextual patterns.

eleuther_acts_top20 · claude-3-7-sonnet-20250219 Triggered by @lu-christina

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

AnchorStyles

-0.35

tran

-0.34

 audit

-0.31

inely

-0.31

 Armed

-0.30

TokenNameLPAREN

-0.30

 lievito

-0.30

RuleContext

-0.30

OnClickListener

-0.30

paras

-0.29

POSITIVE LOGITS

EDEFAULT

0.68

awtextra

0.65

 surla

0.60

 defaultstate

0.59

:✨

0.59

SharedCtor

0.56

MigrationBuilder

0.54

 المعيارى

0.54

 AssemblyCulture

0.53

 &___

0.52

Activations Density 0.267%

references to statistical or experimental data and comparisons

Technical terminology, units, or named variants in formal/academic documents, often preceding punctuation or appearing in specific contextual patterns.

No Comments

No Known Activations

references to statistical or experimental data and comparisons

Technical terminology, units, or named variants in formal/academic documents, often preceding punctuation or appearing in specific contextual patterns.

No Comments

No Known Activations