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

0:0.08

1:0.06

2:0.09

3:0.07

4:0.09

5:0.08

6:0.08

7:0.08

8:0.08

9:0.09

10:0.06

11:0.08

Negative Logits

aunt

-1.83

 Intercept

-1.82

 Ammunition

-1.71

 fame

-1.69

 tossed

-1.68

Hur

-1.66

Fil

-1.66

 struck

-1.62

 silenced

-1.62

tones

-1.62

POSITIVE LOGITS

actively

1.99

independent

1.97

aeda

1.82

›

1.81

earch

1.80

ially

1.75

rogram

1.75

ective

1.74

clock

1.72

hematically

1.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.