INDEX

Explanations

references to "base" and related terms 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyTitle

-0.86

 paja

-0.80

 NSCoder

-0.69

 McQu

-0.68

СТВ

-0.64

 écl

-0.64

 VICT

-0.63

 emballage

-0.63

publique

-0.62

loroethene

-0.60

POSITIVE LOGITS

 bases

1.85

 base

1.85

 Bases

1.72

Bases

1.70

 Base

1.68

BAS

1.65

bases

1.62

 BASE

1.59

BAS

1.55

base

1.55

Activations Density 0.091%

references to "base" and related terms in various contexts

No Comments

No Known Activations