INDEX

Explanations

terms related to errors and corrections in data or documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

WithIOException

-0.64

complexContent

-0.62

 Administrativna

-0.61

 GetEnumerator

-0.58

endsection

-0.57

cplusplus

-0.55

 BorderLayout

-0.53

 autorytatywna

-0.52

heav

-0.52

 MotionEvent

-0.51

POSITIVE LOGITS

 errors

1.05

 error

0.99

 mistakes

0.96

 incorrect

0.96

 inaccuracies

0.95

 inaccurate

0.94

 mistake

0.93

 erroneous

0.92

 inaccuracy

0.92

errors

0.91

Activations Density 0.870%

terms related to errors and corrections in data or documentation

No Comments

No Known Activations