INDEX

Explanations

attends to characters or terms related to user libraries from additional library elements

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

0:0.03

1:0.04

2:0.05

3:0.08

4:0.04

5:0.53

6:0.12

7:0.07

Negative Logits

 fund

-0.26

-0.24

wä

-0.23

 Fiche

-0.22

 تق

-0.22

 houſe

-0.22

 house

-0.22

askin

-0.22

)";

-0.21

POSITIVE LOGITS

TagMode

0.53

AnchorTagHelper

0.46

:✨

0.44

TypedDataSet

0.44

SpringRunner

0.44

دانشنامهٔ

0.43

WithIOException

0.42

ConstraintMaker

0.42

adpleegd

0.41

 otomatig

0.41

Activations Density 0.021%

attends to characters or terms related to user libraries from additional library elements

No Comments

No Known Activations