INDEX

Explanations

commands or suggestions to try something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

NUMX

-0.78

élène

-0.73

 ―――――

-0.72

 becauſe

-0.69

 Theſe

-0.69

 itſelf

-0.68

 Reſ

-0.68

 LEYENDO

-0.67

 Houſe

-0.67

 Etrus

-0.66

POSITIVE LOGITS

Try

0.96

Try

0.88

try

0.88

 Apply

0.81

Apply

0.79

]")]

0.69

try

0.69

 apply

0.64

APPLY

0.64

TRY

0.64

Activations Density 0.140%

commands or suggestions to try something

No Comments

No Known Activations