INDEX

Explanations

expressions or phrases related to responses and feedback in communication contexts

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

"response" or its variations

np_acts-logits-general · gemini-2.0-flash

immune response

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

UrlResolution

-0.68

__':

-0.67

verwijspagina

-0.65

LLocation

-0.65

 ujednoznacz

-0.64

 esternos

-0.63

 intptr

-0.59

EDEFAULT

-0.59

 AssemblyVersion

-0.57

POSITIVE LOGITS

 response

3.24

 responses

2.79

 Response

2.78

response

2.77

 respond

2.74

 RESPONSE

2.57

 responded

2.56

Response

2.56

 responds

2.52

 responding

2.49

Activations Density 0.817%

expressions or phrases related to responses and feedback in communication contexts

"response" or its variations

immune response

No Comments

No Known Activations