INDEX

Explanations

references to documentation and API details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 متعلقه

-0.93

Hochspringen

-0.89

SpringRunner

-0.85

 pleaſure

-0.83

__":

-0.82

__':

-0.80

prnewswire

-0.80

quelize

-0.79

//

-0.79

 emper

-0.77

POSITIVE LOGITS

doc

2.39

doc

2.34

Doc

2.26

Doc

2.25

DOC

1.90

DOC

1.72

 docs

1.59

 Docs

1.54

docs

1.48

Docs

1.47

Activations Density 0.042%

references to documentation and API details

No Comments

No Known Activations