INDEX

Explanations

terms associated with cutting and tool descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Drake

-0.57

 Bullock

-0.54

Drake

-0.54

 ResponseEntity

-0.51

MockBean

-0.50

 drake

-0.50

UniformLocation

-0.49

 Dany

-0.48

drake

-0.48

 Dowling

-0.48

POSITIVE LOGITS

 cutting

2.38

cut

2.29

 Cutting

2.29

Cut

2.19

Cutting

2.17

 cuts

2.17

cutting

2.10

Cut

2.08

 Cuts

2.06

cut

2.02

Activations Density 0.721%

terms associated with cutting and tool descriptions

No Comments

No Known Activations