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

0:0.10

1:0.07

2:0.09

3:0.09

4:0.07

5:0.08

6:0.08

7:0.08

8:0.07

9:0.08

10:0.07

11:0.07

Negative Logits

erness

-2.34

loo

-2.24

eared

-2.18

rower

-2.04

ymm

-2.01

ylum

-1.99

chanted

-1.97

rang

-1.97

ansson

-1.96

isle

-1.93

POSITIVE LOGITS

 guiActiveUn

2.41

 Tuls

2.08

 councill

1.98

 cull

1.89

 typh

1.86

Pinterest

1.83

Clean

1.82

 tsunami

1.80

 morale

1.80

 Analy

1.79

Activations Density 0.000%

No Known Activations

This feature has no known activations.