INDEX

Explanations

terms related to references and citations

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

cstdlib

-0.72

ForRow

-0.71

:✨

-0.71

colage

-0.69

lück

-0.69

wps

-0.68

 fileSize

-0.67

Tyl

-0.67

ADP

-0.67

 BOOL

-0.65

POSITIVE LOGITS

 reference

2.54

 Reference

2.32

Reference

2.30

reference

2.21

 references

2.19

 REFERENCE

2.10

 References

1.90

REFERENCE

1.86

References

1.84

references

1.78

Activations Density 0.182%

terms related to references and citations

No Comments

No Known Activations