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

2:0.09

3:0.07

4:0.07

5:0.07

6:0.07

7:0.08

8:0.07

9:0.08

10:0.08

11:0.09

Negative Logits

 omit

-2.55

 omitted

-2.30

ewitness

-2.16

 publish

-2.15

 substituted

-2.13

 discard

-2.05

 swapped

-2.02

letter

-2.01

/*

-1.96

 reprint

-1.96

POSITIVE LOGITS

gging

2.06

 Morales

2.06

 Investigator

2.04

IER

2.03

 Funds

1.98

jandro

1.98

uman

1.97

Els

1.94

 Liberals

1.91

DonaldTrump

1.90

Activations Density 0.000%

No Known Activations

This feature has no known activations.