INDEX

Explanations

attends to the token "extends" from class-related tokens

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.05

1:0.02

2:0.02

3:0.02

4:0.69

5:0.05

6:0.05

7:0.06

Negative Logits

__(/*!

-0.37

 <=",

-0.35

ragalactic

-0.33

PyExc

-0.33

الإنجليزية

-0.32

IUrlHelper

-0.31

politico

-0.30

 Infórmanos

-0.30

 host

-0.30

host

-0.30

POSITIVE LOGITS

 EconPapers

0.46

Tembelea

0.45

 denke

0.40

ptonshire

0.38

owohl

0.37

 antaranya

0.37

meanor

0.36

 oublié

0.36

более

0.36

 MessageBoxIcon

0.36

Activations Density 0.086%

attends to the token "extends" from class-related tokens

No Comments

No Known Activations