INDEX

Explanations

references to individuals, particularly in a legal or scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

NTB

-0.79

Efq

-0.79

ALR

-0.78

ruptedException

-0.78

AccessorTable

-0.78

SDC

-0.78

 Makassar

-0.77

tská

-0.77

 Mard

-0.77

 pleaſure

-0.77

POSITIVE LOGITS

Spa

0.83

 Pipe

0.73

 Oven

0.73

Oven

0.72

spa

0.72

Bat

0.71

Tub

0.71

'));

0.70

]));

0.66

Pipe

0.65

Activations Density 1.940%

references to individuals, particularly in a legal or scientific context

No Comments

No Known Activations