INDEX

Explanations

references to scientific research or citations

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

Tokens before a number enclosed in "[@...@]"

np_acts-logits-general · gemini-2.0-flash

citations, references

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 purpoſe

-1.04

 houſe

-1.03

AndEndTag

-0.99

 kasarigan

-0.98

RenderAtEndOf

-0.98

 uſe

-0.97

 perſon

-0.97

 ſta

-0.97

 preſent

-0.95

 Houſe

-0.95

POSITIVE LOGITS

0.49

0.48

0.46

0.45

träge

0.42

0.41

0.40

Activations Density 0.565%

references to scientific research or citations

Tokens before a number enclosed in "[@...@]"

citations, references

No Comments

No Known Activations