INDEX

Explanations

expressions indicating a lack or absence of something

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

Following "no" or words indicating lack of knowledge/ability

np_acts-logits-general · gemini-2.0-flash

no [noun]

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

 AssemblyTitle

-0.73

]='\

-0.63

yorsunuz

-0.61

 préférable

-0.61

 plenty

-0.59

reszcie

-0.58

fecture

-0.58

 متعلقه

-0.53

onomía

-0.52

enterOuterAlt

-0.52

POSITIVE LOGITS

 clue

0.83

 regard

0.69

 fucks

0.68

 idea

0.67

say

0.64

 qual

0.63

 recourse

0.61

 concept

0.60

 trace

0.60

 sympathy

0.59

Activations Density 0.182%

expressions indicating a lack or absence of something

Following "no" or words indicating lack of knowledge/ability

no [noun]

No Comments

No Known Activations