INDEX

Explanations

references to walls and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Judson

-0.80

 temprana

-0.80

 Plural

-0.76

 foncé

-0.76

 ujednoznacz

-0.76

 wezen

-0.74

 noires

-0.73

 pleaſure

-0.73

 inoxydable

-0.73

epam

-0.73

POSITIVE LOGITS

 wall

2.00

 WALL

1.91

 Wall

1.89

 walls

1.81

Wall

1.76

wall

1.72

 Walls

1.66

WALL

1.61

Walls

1.53

walls

1.53

Activations Density 0.054%

references to walls and their characteristics

No Comments

No Known Activations