INDEX

Explanations

attends to periods from tokens that signify the titles or roles of doctors in various contexts

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

0:0.07

1:0.08

2:0.15

3:0.14

4:0.09

5:0.15

6:0.13

7:0.15

Negative Logits

 myſelf

-12.50

 itſelf

-12.06

Efq

-11.75

 Monfieur

-11.31

 Theſe

-10.88

 Jefus

-10.81

 ―――――

-10.69

 pleaſure

-10.63

 Majefty

-10.56

 themſelves

-10.44

POSITIVE LOGITS

6.53

6.31

5.88

5.56

↵↵

5.53

<eos>

5.31

in

5.09

4.81

4.78

Activations Density 2.105%

attends to periods from tokens that signify the titles or roles of doctors in various contexts

No Comments

No Known Activations