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

0:0.09

1:0.06

2:0.09

3:0.08

4:0.08

5:0.09

6:0.08

7:0.07

8:0.09

9:0.07

10:0.08

11:0.07

Negative Logits

 overhe

-1.78

 masturb

-1.75

 phot

-1.66

 paraph

-1.60

cipled

-1.54

 premature

-1.53

 hypothetical

-1.51

 uncomp

-1.46

EStreamFrame

-1.45

 retro

-1.42

POSITIVE LOGITS

aceae

1.91

 Tart

1.74

 Lancet

1.73

igers

1.72

akia

1.69

arant

1.67

antage

1.63

atures

1.62

arie

1.60

oku

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.