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

0:0.09

1:0.08

2:0.09

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

��

-2.43

 Meridian

-2.04

Union

-2.02

 neighbour

-1.99

incial

-1.86

Weather

-1.84

 Weather

-1.83

 Ulster

-1.82

States

-1.81

 Streets

-1.81

POSITIVE LOGITS

ahime

2.70

beit

2.35

rers

2.33

 convinc

1.99

prising

1.96

ldom

1.96

eryl

1.92

ッド

1.91

prisingly

1.90

rame

1.88

Activations Density 0.000%

No Known Activations

This feature has no known activations.