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

0:0.08

1:0.08

2:0.08

3:0.07

4:0.07

5:0.08

6:0.09

7:0.10

8:0.06

9:0.08

10:0.08

11:0.09

Negative Logits

 Secondly

-2.31

[/

-2.11

↵

-2.09

Characters

-2.04

 Variant

-2.03

atos

-1.98

ATA

-1.94

 Administ

-1.94

ATES

-1.93

Second

-1.84

POSITIVE LOGITS

luaj

2.10

inia

2.09

qus

2.04

otte

1.96

amia

1.93

ocry

1.93

 Tome

1.87

か

1.86

thora

1.85

fle

1.85

Activations Density 0.000%

No Known Activations

This feature has no known activations.