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

0:0.09

1:0.07

2:0.08

3:0.09

4:0.08

5:0.07

6:0.08

7:0.08

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

IJ

-3.34

 Hector

-3.05

Jose

-2.84

AFP

-2.83

iere

-2.71

Tue

-2.70

alian

-2.69

rique

-2.67

north

-2.66

bian

-2.65

POSITIVE LOGITS

 synerg

2.90

 Lovecraft

2.87

pmwiki

2.77

 Regener

2.69

 Zombie

2.62

 Ghostbusters

2.61

 symb

2.58

 Cycle

2.55

 generators

2.53

Quantity

2.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.