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

3:0.07

4:0.09

5:0.09

6:0.07

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 Camer

-1.61

 Kahn

-1.55

 Kard

-1.54

 Brett

-1.53

 Kaufman

-1.51

 underdog

-1.50

 stereo

-1.48

 strugg

-1.43

 Pict

-1.39

 fledgling

-1.39

POSITIVE LOGITS

idav

1.73

achus

1.69

gaard

1.69

 Oaks

1.69

otom

1.67

iliar

1.65

闘

1.60

choice

1.59

idelines

1.58

agus

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.