INDEX

Explanations

interactions involving questioning and dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

IUrlHelper

-0.89

 ComVisible

-0.58

 særlig

-0.58

'])->

-0.56

 fær

-0.54

ajur

-0.52

photobucket

-0.51

 singoli

-0.51

SYNOPSIS

-0.50

aarrggbb

-0.50

POSITIVE LOGITS

 replied

0.71

 verbally

0.68

 politely

0.65

 reply

0.64

 conversation

0.64

 Polite

0.59

Ihm

0.59

 Discus

0.56

 told

0.56

 Asked

0.55

Activations Density 0.547%

interactions involving questioning and dialogue

No Comments

No Known Activations