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

2:0.08

3:0.08

4:0.07

5:0.08

6:0.08

7:0.09

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

edly

-1.84

vous

-1.72

oppers

-1.69

rounder

-1.65

endez

-1.63

bery

-1.61

avia

-1.61

esi

-1.60

elope

-1.59

mented

-1.55

POSITIVE LOGITS

�

1.94

 vapor

1.57

��

1.53

 privileges

1.49

 advis

1.46

�

1.46

 rein

1.44

 Guth

1.42

Hard

1.42

 perks

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.