INDEX

Explanations

references to medical procedures and techniques

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

Text followed by "block" or "blocks"

np_acts-logits-general · gemini-2.0-flash

building blocks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

findpost

-0.57

canestro

-0.45

tour

-0.44

发表于

-0.44

 তারিখ

-0.44

Tour

-0.43

 tour

-0.43

Daughter

-0.43

 Tour

-0.43

lapi

-0.43

POSITIVE LOGITS

 block

4.56

 Block

4.22

block

4.16

Block

3.99

 blocks

3.87

 BLOCK

3.86

 Blocks

3.58

BLOCK

3.54

blocks

3.36

Blocks

3.23

Activations Density 0.232%

references to medical procedures and techniques

Text followed by "block" or "blocks"

building blocks

No Comments

No Known Activations