INDEX

Explanations

attends to the token "Category" from various category 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

0:0.02

1:0.05

2:0.43

3:0.12

4:0.06

5:0.10

6:0.08

7:0.10

Negative Logits

the

-0.82

it

-0.69

-0.68

all

-0.64

an

-0.59

is

-0.59

in

-0.58

The

-0.58

or

-0.58

POSITIVE LOGITS

 Shakspeare

0.99

 photolibrary

0.96

 crdi

0.93

 cdti

0.91

Personendaten

0.91

verwijspagina

0.91

 tfsi

0.89

 moschino

0.88

 negroes

0.88

 sherds

0.88

Activations Density 5.299%

attends to the token "Category" from various category tokens

No Comments

No Known Activations