INDEX

Explanations

expressions of imagination and self-reflection

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

⋮

-0.63

riwal

-0.61

bouncycastle

-0.59

 leçon

-0.59

談社

-0.59

romycin

-0.56

Beijos

-0.55

meteries

-0.54

gewiesen

-0.54

 QLabel

-0.53

POSITIVE LOGITS

 imagining

2.06

 imagine

2.04

 imagined

1.92

Imagine

1.88

 imagin

1.88

 Imagine

1.87

 imagines

1.86

 Imagin

1.85

imagine

1.81

Imagin

1.76

Activations Density 0.155%

expressions of imagination and self-reflection

No Comments

No Known Activations