INDEX

Explanations

references to specific "points" or indicators in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ChildScrollView

-0.96

 HasFactory

-0.92

ercito

-0.82

 Theſe

-0.82

 DELLE

-0.80

 umani

-0.79

(!__

-0.76

 OFDb

-0.76

 MainAxisSize

-0.75

GraphicsUnit

-0.74

POSITIVE LOGITS

 POINT

1.74

 point

1.69

 points

1.63

 Point

1.60

point

1.59

POINT

1.54

 Points

1.47

Point

1.46

points

1.44

 POINTS

1.44

Activations Density 0.078%

references to specific "points" or indicators in various contexts

No Comments

No Known Activations