INDEX

Explanations

expressions of acceptance or approval

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

verwijspagina

-0.64

 CURIAM

-0.56

flashdata

-0.56

 старости

-0.54

rairie

-0.53

 GoogleFonts

-0.53

atchewan

-0.52

WebpackPlugin

-0.52

HideInInspector

-0.51

POSITIVE LOGITS

 accept

4.37

 acceptance

4.04

 accepted

4.02

 accepting

3.98

 Accept

3.95

accept

3.91

 ACCEPT

3.83

 accepts

3.83

 Accepting

3.73

Accept

3.70

Activations Density 0.066%

expressions of acceptance or approval

No Comments

No Known Activations