INDEX

Explanations

attends to specific scientific terms related to organisms or plant species from tokens that discuss varied subjects

oai_attention-head · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.attn.hook_z

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.28

2:0.44

3:0.02

4:0.03

5:0.04

6:0.04

7:0.08

Negative Logits

 Shakspeare

-0.35

 deschis

-0.34

 noastre

-0.34

 Cæsar

-0.33

ReusableCell

-0.33

TagMode

-0.32

 servici

-0.31

 cuno

-0.30

 photolibrary

-0.30

 chopsticks

-0.30

POSITIVE LOGITS

addCriterion

0.41

principalColumn

0.36

dfunding

0.35

rova

0.35

trine

0.35

ndal

0.34

niana

0.34

︡

0.34

ENSA

0.34

ZAS

0.34

Activations Density 0.017%

attends to specific scientific terms related to organisms or plant species from tokens that discuss varied subjects

No Comments

No Known Activations