INDEX

Explanations

terms related to buying or acquiring items

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 '\\;'

-1.19

nastics

-0.76

DockStyle

-0.69

httphttps

-0.68

 AspNetCore

-0.64

 Didi

-0.63

bbene

-0.63

/\.

-0.62

 bitters

-0.61

 betweenstory

-0.60

POSITIVE LOGITS

 purchase

3.74

 purchasing

3.50

 buying

3.40

 purchased

3.24

 purchases

3.16

 Purchase

3.13

purchase

3.10

buy

3.03

 buys

3.02

 bought

3.01

Activations Density 0.066%

terms related to buying or acquiring items

No Comments

No Known Activations