INDEX

Explanations

specific categories and classifications within a set of data

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

Common connecting words and phrases that establish relationships between concepts or provide specification in technical, academic, or structured text.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Autoritní

-0.73

bootstrapcdn

-0.60

WEBPACK

-0.54

Personendaten

-0.54

UrlResolution

-0.49

 HasFactory

-0.48

 doInBackground

-0.48

InInspector

-0.47

initializeApp

-0.47

 оригіналу

-0.46

POSITIVE LOGITS

 individual

0.48

rungsseite

0.43

 specifically

0.43

 specific

0.42

 SPECIFIC

0.40

 specifics

0.40

tvguidetime

0.39

individual

0.39

specific

0.39

 từng

0.38

Activations Density 0.085%

specific categories and classifications within a set of data

Common connecting words and phrases that establish relationships between concepts or provide specification in technical, academic, or structured text.

No Comments

No Known Activations