INDEX

Explanations

references to walls 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Judson

-0.81

 temprana

-0.80

epam

-0.75

})));

-0.75

észetes

-0.74

 wezen

-0.73

Prat

-0.73

 themſelves

-0.73

 jonge

-0.70

 pleaſure

-0.69

POSITIVE LOGITS

 wall

2.38

 WALL

2.29

 Wall

2.27

Wall

2.10

 walls

2.10

wall

2.06

WALL

1.94

 Walls

1.92

walls

1.78

Walls

1.75

Activations Density 0.036%

references to walls in various contexts

No Comments

No Known Activations