INDEX

Explanations

terms related to scientific or technical contexts, particularly in biochemical and environmental discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.89

 appunto

-0.74

™.

-0.67

®.

-0.65

.\\

-0.64

[toxicity=0]

-0.63

 lainnya

-0.61

。

-0.58

 respectivamente

-0.58

POSITIVE LOGITS

Geplaatst

1.03

 ModelExpression

1.02

SourceChecksum

1.02

AndEndTag

0.99

webElementXpaths

0.93

InjectAttribute

0.92

 ProtoMessage

0.90

EndGlobalSection

0.88

MessageOf

0.87

 disambiguazione

0.87

Activations Density 1.009%

terms related to scientific or technical contexts, particularly in biochemical and environmental discussions

No Comments

No Known Activations