INDEX

Explanations

terms related to logarithmic functions and their properties

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

 itſelf

-1.15

 snippetHide

-1.09

 Theſe

-1.04

Geplaatst

-1.04

 myſelf

-1.01

 Houſe

-0.98

 Shakspeare

-0.97

 تانيه

-0.97

 utafitiHapana

-0.96

 AssemblyCulture

-0.96

POSITIVE LOGITS

log

1.02

log

0.98

Log

0.83

des

0.82

Log

0.80

des

0.74

 Serv

0.72

Des

0.71

 Youth

0.70

Serv

0.69

Activations Density 0.129%

terms related to logarithmic functions and their properties

No Comments

No Known Activations