INDEX

Explanations

terms related to internal and external factors 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 @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

enumi

-1.04

LogFactory

-0.91

 astronomers

-0.85

 Wors

-0.81

 végétale

-0.80

 revista

-0.79

OGND

-0.79

kháu

-0.79

 Roskov

-0.78

 suivants

-0.78

POSITIVE LOGITS

 internal

2.12

 external

2.08

 External

1.92

 Internal

1.90

external

1.84

External

1.81

Internal

1.79

internal

1.77

 INTERNAL

1.75

 EXTERNAL

1.67

Activations Density 0.050%

terms related to internal and external factors in various contexts

No Comments

No Known Activations