INDEX

Explanations

technical terms and cues related to programming or system operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 either

-1.17

Either

-1.16

-1.14

 Either

-1.14

either

-1.12

 bądź

-1.05

 entweder

-0.96

 oppure

-0.89

-0.86

 albo

-0.85

POSITIVE LOGITS

########.

1.08

Personendaten

0.94

ReusableCell

0.94

Autoritní

0.88

ResumeLayout

0.88

Datuak

0.87

 Мексичка

0.86

 مرئيه

0.84

 AssemblyCulture

0.82

ViewFeatures

0.82

Activations Density 0.252%

technical terms and cues related to programming or system operations

No Comments

No Known Activations