INDEX

Explanations

attends from tokens to the second token indexed with 1 in the sequence

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

0:0.22

1:0.05

2:0.04

3:0.04

4:0.03

5:0.06

6:0.03

7:0.49

Negative Logits

-2.91

-2.84

-2.39

-2.33

-2.31

-2.25

-2.22

-2.19

-2.11

POSITIVE LOGITS

BibitemShut

2.03

ratulations

1.99

—

1.96

"):

1.93

'):

1.91

')):

1.88

%");

1.88

%\]

1.88

]--;

1.84

FTFY

1.80

Activations Density 0.332%

attends from tokens to the second token indexed with 1 in the sequence

No Comments

No Known Activations