INDEX

Explanations

key components and relationships within narrative structures or descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 myſelf

-0.79

 Jefus

-0.76

ſelf

-0.71

 témoin

-0.70

 preſent

-0.68



-0.67

 fubject

-0.66

 whoſe

-0.65

 feroit

-0.65

 auffi

-0.64

POSITIVE LOGITS

 acceptable

1.09

 forgive

1.09

 tolerate

1.07

 forgiven

1.07

 accept

1.05

 tolerated

1.05

 forgiving

1.00

 tolerable

0.99

toler

0.98

 toler

0.98

Activations Density 0.339%

key components and relationships within narrative structures or descriptions

No Comments

No Known Activations