INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.06

2:0.09

3:0.08

4:0.08

5:0.07

6:0.06

7:0.07

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

inea

-1.95

Dial

-1.81

ida

-1.79

ergic

-1.79

 Inher

-1.77

uren

-1.76

kees

-1.74

sted

-1.67

leans

-1.65

ilet

-1.61

POSITIVE LOGITS

 subscription

1.91

 Ples

1.81

Geo

1.80

 satellite

1.76

nces

1.76

 gulf

1.69

 quotas

1.67

 hostile

1.67

 ther

1.65

reality

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.