INDEX

Explanations

scientific classifications or categories in biological contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

-2.68

 Monfieur

-2.65

 itſelf

-2.60

Efq

-2.46

 pleaſure

-2.35

 purpoſe

-2.35

 Jefus

-2.32

 Anſ

-2.30

 Houſe

-2.28

 Theſe

-2.27

POSITIVE LOGITS

1.06

0.86

<eos>

0.85

0.84

0.83

↵↵

0.83

Activations Density 0.295%

scientific classifications or categories in biological contexts

No Comments

No Known Activations