INDEX

Explanations

references to slugs and terms associated with them, particularly in a negative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 createStore

-0.83

 Elbe

-0.81

CreateModel

-0.79

 Sandi

-0.77

 Minato

-0.76

 Lora

-0.72

angelo

-0.72

 drap

-0.72

 Borne

-0.72

 Blackwell

-0.71

POSITIVE LOGITS

ug

1.42

UG

1.32

ug

1.10

Mug

1.09

Nug

1.07

Mug

1.06

ugs

1.02

Pug

1.00

jug

0.97

Lug

0.96

Activations Density 0.014%

references to slugs and terms associated with them, particularly in a negative context

No Comments

No Known Activations