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

0:0.07

1:0.08

2:0.08

3:0.08

4:0.10

5:0.08

6:0.07

7:0.09

8:0.08

9:0.06

10:0.07

11:0.08

Negative Logits

jah

-2.06

interrupted

-1.72

 remem

-1.69

allery

-1.68

Dream

-1.64

 Southwest

-1.63

soft

-1.61

uberty

-1.59

 Shame

-1.58

 regrets

-1.56

POSITIVE LOGITS

otine

1.84

 Legislation

1.76

 motions

1.64

\":

1.63

itors

1.59

division

1.58

エル

1.56

 incoming

1.55

 molecules

1.55

 cannibal

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.