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

0:0.07

1:0.08

2:0.08

3:0.09

4:0.07

5:0.08

6:0.07

7:0.07

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

 hatched

-2.82

aud

-2.79

 gays

-2.79

 disco

-2.76

 plots

-2.71

 stag

-2.69

 reel

-2.67

fug

-2.63

 prostitutes

-2.61

 rats

-2.61

POSITIVE LOGITS

 Unified

2.97

Wra

2.85

 Supports

2.85

 Predator

2.70

uture

2.70

�

2.65

 Expedition

2.64

 Warrant

2.60

 Compatibility

2.58

Tools

2.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.