INDEX

Explanations

references to scenes in a narrative context

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

Agen

-0.46

+#+#

-0.43

اض

-0.43

einander

-0.42

NHL

-0.42

ุม

-0.42

 солдат

-0.41

BankAccount

-0.41

 ader

-0.41

 RSSSF

-0.41

POSITIVE LOGITS

 المعيارى

1.04

ConstraintMaker

0.97

tvguidetime

0.92

 AttributeSet

0.90

 doInBackground

0.90



0.89

IntoConstraints

0.88

CloseOperation

0.87

 صوتيه

0.83

InSection

0.80

Activations Density 0.152%

references to scenes in a narrative context

No Comments

No Known Activations