INDEX

Explanations

general terms and punctuation that may indicate formatting or structural elements in the text

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

 myſelf

-1.93

 itſelf

-1.91

Efq

-1.81

 Monfieur

-1.79

ſelf

-1.78

ſelves

-1.78

 Theſe

-1.74

 Jefus

-1.74

 ―――――

-1.73

 themſelves

-1.72

POSITIVE LOGITS

1.45

<eos>

1.23

↵↵

1.09

1.02

1.01

...

1.00

0.99

to

0.97

Activations Density 0.949%

general terms and punctuation that may indicate formatting or structural elements in the text

No Comments

No Known Activations