INDEX

Explanations

references to documenting, analyzing, or characterizing information and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

se

-0.51

ch

-0.49

do

-0.46

-0.44

pus

-0.44

ic

-0.44

-0.43

yttä

-0.43

 reconn

-0.43

POSITIVE LOGITS

how

1.17



1.16

InjectAttribute

1.13

DockStyle

1.09

 autorytatywna

1.05

 nahilalakip

1.02

 незавершена

1.01

 CreateTagHelper

1.00

principalTable

0.95

SourceChecksum

0.95

Activations Density 0.906%

references to documenting, analyzing, or characterizing information and processes

No Comments

No Known Activations