INDEX

Explanations

references to paper-related products or materials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RuleContext

-0.55

 cím

-0.53

Chú

-0.51

SuccessListener

-0.51

χαν

-0.51

HttpFoundation

-0.50

 EdgeInsets

-0.50

 compelling

-0.50

 Hurley

-0.49

 Seeing

-0.49

POSITIVE LOGITS

 Paper

1.08

Paper

0.99

ArrowToggle

0.92

paper

0.90

 PAPER

0.82

<bos>

0.77

 Papers

0.77

Follow

0.74

PAPER

0.74

Papers

0.74

Activations Density 0.117%

references to paper-related products or materials

No Comments

No Known Activations