INDEX

Explanations

references to various forms of evidence

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

ArgsConstructor

-0.68

 &___

-0.66

 كومونز

-0.58

IUrlHelper

-0.56

Espèce

-0.56

ГЛА

-0.55

/*---

-0.55

 Процитовано

-0.55

filepath

-0.54

!*\

-0.54

POSITIVE LOGITS

 evidence

1.32

evidence

1.22

 Evidence

1.20

Evidence

1.18

 EVIDENCE

1.13

 evidences

0.89

 evidencia

0.82

 evidenced

0.78

Evid

0.75

^(@)

0.72

Activations Density 0.168%

references to various forms of evidence

No Comments

No Known Activations