INDEX

Explanations

references to signals in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Personendaten

-0.88

...");

-0.75

 دیکھیے

-0.72

SPATH

-0.68

 chronique

-0.66

 defaultstate

-0.66

 INSEE

-0.66

 Voici

-0.65

 '\\;'

-0.65

 ")");

-0.65

POSITIVE LOGITS

 signal

1.04

Cy

0.99

Lib

0.95

Lib

0.93

Cy

0.92

signal

0.88

 Signal

0.85

cy

0.84

Signal

0.81

+#+#

0.78

Activations Density 0.100%

references to signals in various contexts

No Comments

No Known Activations