INDEX

Explanations

references to entities within a specific framework

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Shakspeare

-0.93

 pleaſure

-0.92

 OkHttpClient

-0.91

<<-

-0.90

isSuccessful

-0.90

 ſever

-0.90

 Fros

-0.90

JAS

-0.89

 Avignon

-0.89

__(/*!

-0.88

POSITIVE LOGITS

 entity

1.76

entity

1.65

entities

1.65

 entities

1.63

 Entities

1.62

 Entity

1.60

ENTITY

1.57

 ENTITY

1.54

Entities

1.49

Entity

1.45

Activations Density 0.073%

references to entities within a specific framework

No Comments

No Known Activations