INDEX

Explanations

mathematical expressions and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 them

-0.53

Dış

-0.48

 majority

-0.47

 case

-0.47

égi

-0.45

 inflater

-0.45

etary

-0.45

 Shallow

-0.45

measurable

-0.45

াক

-0.44

POSITIVE LOGITS

 AssemblyProduct

0.86

addPreferredGap

0.76

ValueStyle

0.68

原始内容存档于

0.66

LabelTagHelper

0.63

AndEndTag

0.63

SourceChecksum

0.61

 propOrder

0.61

 AssemblyVersion

0.61

 sumpay

0.61

Activations Density 0.675%

mathematical expressions and symbols

No Comments

No Known Activations