INDEX

Explanations

references to documents and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

mergeFrom

-0.72

ArgsConstructor

-0.71

enumii

-0.68

rrggbb

-0.67

thenReturn

-0.63

 CreateTagHelper

-0.61

makeText

-0.60

Lähteet

-0.60

Viitteet

-0.59

raszamy

-0.59

POSITIVE LOGITS

 documents

0.80

DOC

0.80

doc

0.74

DOC

0.71

 Docs

0.69

 Document

0.68

 Documents

0.68

 document

0.67

documents

0.64

Doc

0.64

Activations Density 0.077%

references to documents and documentation

No Comments

No Known Activations