INDEX

Explanations

references to classes and their definitions in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

InputTagHelper

-0.60

LookAnd

-0.57

FormTagHelper

-0.57

extAlignment

-0.56

kloped

-0.56

ContentAsync

-0.53

transQ

-0.51

execSQL

-0.48

ModelBuilder

-0.46

RegressionTest

-0.45

POSITIVE LOGITS

 reference

1.94

 references

1.80

 Reference

1.71

reference

1.66

 referencia

1.61

 References

1.59

Reference

1.56

 REFERENCE

1.53

 référence

1.52

references

1.51

Activations Density 0.537%

references to classes and their definitions in programming contexts

No Comments

No Known Activations