INDEX

Explanations

references to storytelling or narration

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

tagHelperRunner

-0.75

ыгана

-0.70

UnknownFields

-0.68

AnchorStyles

-0.68

 AssemblyProduct

-0.67

InjectAttribute

-0.67

IPAC

-0.64

contentLoaded

-0.61

 virke

-0.61

),

-0.61

POSITIVE LOGITS

 tells

1.21

 Tells

1.05

 tell

1.05

 told

1.00

 telling

0.99

telling

0.97

 Tell

0.96

 Told

0.90

tells

0.89

tell

0.87

Activations Density 0.204%

references to storytelling or narration

No Comments

No Known Activations