INDEX

Explanations

words or phonemes related to specific patterns in written or spoken language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 adic

-0.69

 Theſe

-0.66

 gema

-0.60

APE

-0.59

 inverte

-0.59

 intuiti

-0.59

 avis

-0.59

 Dazu

-0.58

 talle

-0.58

 Alles

-0.57

POSITIVE LOGITS

tagext

0.97

nvarchar

0.95

 nakalista

0.94

0.91

0.90

𝙫

0.87

'',

0.87

0.86

setH

0.84

0.83

Activations Density 0.161%

words or phonemes related to specific patterns in written or spoken language

No Comments

No Known Activations