INDEX

Explanations

references to source materials or citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Iw

-0.69

 outputStream

-0.65

wps

-0.63

 getY

-0.63

ADP

-0.62

 Tokyo

-0.61

orney

-0.61

 hơi

-0.61

PackageName

-0.60

 Henn

-0.60

POSITIVE LOGITS

 useRef

1.66

 Refs

1.26

 refs

1.24

 reference

1.22

REF

1.18

 Reference

1.17

Refer

1.17

 ElementRef

1.17

 refer

1.17

 references

1.17

Activations Density 0.218%

references to source materials or citations

No Comments

No Known Activations