INDEX

Explanations

terms related to contextual situations or frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

-0.69

✨:

-0.67

didSet

-0.63

DockStyle

-0.54

ModelAdmin

-0.54

CppMethod

-0.54

 QLabel

-0.50

QLabel

-0.50

 étanche

-0.49

tagez

-0.49

POSITIVE LOGITS

 context

4.12

context

3.74

 Context

3.50

Context

3.28

 CONTEXT

3.09

 contexts

3.02

 contexto

2.84

CONTEXT

2.69

 contex

2.67

 contexte

2.53

Activations Density 0.088%

terms related to contextual situations or frameworks

No Comments

No Known Activations