INDEX

Explanations

statements or assertions that present new concepts or insights

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

Sentences starting with "This"

np_acts-logits-general · gemini-2.0-flash

introduces a finding or explanation

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

WithIOException

-0.74

 '\\;'

-0.71

sizeCache

-0.58

 समीक्षाएं

-0.56

 eventdata

-0.56

 eccell

-0.55

 specifik

-0.54

 AssemblyTitle

-0.54

verwijspagina

-0.53

Rhestr

-0.53

POSITIVE LOGITS

 latter

0.81

 method

0.77

 process

0.71

 approach

0.71

latter

0.69

EndContext

0.64

 result

0.63

 kind

0.63

 type

0.60

 idea

0.58

Activations Density 0.407%

statements or assertions that present new concepts or insights

Sentences starting with "This"

introduces a finding or explanation

No Comments

No Known Activations