INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.07

1:0.07

2:0.08

3:0.07

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.09

10:0.08

11:0.09

Negative Logits

 Norton

-3.08

PSU

-2.94

hess

-2.80

oard

-2.80

cone

-2.69

 routing

-2.65

pav

-2.59

 lockdown

-2.49

 Bates

-2.48

 Nunes

-2.48

POSITIVE LOGITS

%%

3.89

神

2.96

%:

2.84

%%

2.81

 Lean

2.75

emale

2.66

rior

2.62

</

2.60

 verbs

2.59

mast

2.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.