INDEX

Explanations

statements and evidence that support claims or conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kloped

-0.54

yaf

-0.47

 claro

-0.46

CopyWith

-0.46

 متعلقه

-0.44

 uninsured

-0.44

 chiaro

-0.44

 GoogleFonts

-0.44

crollView

-0.44

 Docket

-0.44

POSITIVE LOGITS

 GenerationType

0.69

GEBURTSDATUM

0.66

validates

0.60

__':

0.58

الدراسه

0.58

 AssemblyVersion

0.58

hypothesis

0.57

__':

0.56

SqlClient

0.55

++]=

0.54

Activations Density 1.149%

statements and evidence that support claims or conclusions

No Comments

No Known Activations