INDEX

Explanations

phrases indicating prior actions or ongoing situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 CreateTagHelper

-0.97

twimg

-0.94

 كومونز

-0.94

__":

-0.90

 defaultstate

-0.89

 propOrder

-0.86

DockStyle

-0.81

errHandler

-0.80

MLLoader

-0.80

quelize

-0.80

POSITIVE LOGITS

 already

1.28

Already

1.16

already

1.16

 Already

1.12

 ALREADY

0.97

ALREADY

0.87

 déjà

0.75

 уже

0.74

 bereits

0.74

すでに

0.72

Activations Density 0.185%

phrases indicating prior actions or ongoing situations

No Comments

No Known Activations