INDEX

Explanations

technical references to web requests and handling in programming or networking contexts

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

LookAndFeel

-0.61

 typelib

-0.54

 EnglishChoose

-0.48

 faptul

-0.48

 esquecer

-0.45

SneakyThrows

-0.44

DMETHOD

-0.44

 defaultstate

-0.41

/******/

-0.41

 olyan

-0.41

POSITIVE LOGITS

}$.\\

0.92

".

0.88

…).

0.87

 appunto

0.86

 }}$.

0.85

NUMX

0.85

).

0.85

 […]

0.85

.”.

0.83

.*/

0.82

Activations Density 3.138%

technical references to web requests and handling in programming or networking contexts

No Comments

No Known Activations