INDEX

Explanations

values indicating significant numerical results or statistical data

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TeV

-0.85

期刊论文

-0.85

 оригіналу

-0.81

 Frick

-0.80

)))

-0.79

'}';

-0.77

CONSIN

-0.77

 ostavi

-0.75

 hind

-0.75

InjectAttribute

-0.74

POSITIVE LOGITS

 urbanas

0.90

NOPQRST

0.84

ESTAMP

0.68

typeorm

0.68

ازم

0.67

trum

0.67

 Sénat

0.67

atorze

0.67

zeitige

0.66

wanzig

0.65

Activations Density 0.266%

values indicating significant numerical results or statistical data

No Comments

No Known Activations