INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.10

1:0.07

2:0.11

3:0.09

4:0.07

5:0.08

6:0.06

7:0.09

8:0.08

9:0.06

10:0.07

11:0.07

Negative Logits

psy

-2.74

 components

-2.35

 Cincinnati

-2.32

 Magn

-2.32

chet

-2.32

 enhanced

-2.30

 Memphis

-2.30

Dig

-2.27

 strengthened

-2.25

Critical

-2.25

POSITIVE LOGITS

 surn

2.88

 contestant

2.82

 evict

2.77

 answ

2.71

 pronouns

2.69

 loudspe

2.67

 sofa

2.59

 Norn

2.48

 eviction

2.43

 injunction

2.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.