INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

2:0.10

3:0.08

4:0.07

5:0.09

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

emis

-2.03

essee

-2.02

 vans

-1.98

holes

-1.97

JA

-1.94

ember

-1.87

Salt

-1.85

agra

-1.84

lash

-1.82

hunter

-1.80

POSITIVE LOGITS

repeat

2.43

inging

2.26

 Pend

1.94

%%%%

1.89

utterstock

1.85

%:

1.81

akable

1.78

 Blaz

1.77

�

1.76

Synopsis

1.76

Activations Density 0.000%

No Known Activations

This feature has no known activations.