INDEX

Explanations

references to access, particularly in the context of systems, resources, or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Zacks

-0.53

urilor

-0.51

urgery

-0.50

ViewInit

-0.49

 quella

-0.49

 moelle

-0.47

und

-0.46

alias

-0.44

Zacks

-0.44

Obituary

-0.44

POSITIVE LOGITS

 Access

1.06

 access

1.04

 losses

0.98

 Chwiliwch

0.96

 ACCESS

0.90

ACCESS

0.88

Access

0.86

 Losses

0.83

 Anſ

0.82

 صوتيه

0.81

Activations Density 0.129%

references to access, particularly in the context of systems, resources, or information

No Comments

No Known Activations