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

3:0.07

4:0.08

5:0.07

6:0.07

7:0.09

8:0.08

9:0.09

10:0.08

11:0.07

Negative Logits

srf

-2.19

ividual

-2.10

aukee

-2.04

oga

-2.03

 unfocusedRange

-2.01

Square

-1.90

UNE

-1.87

�

-1.87

irtual

-1.86

oba

-1.86

POSITIVE LOGITS

 bailed

2.16

 Lans

2.02

Mess

1.97

 elsewhere

1.94

selves

1.93

 theirs

1.88

 trusts

1.80

 starved

1.80

______

1.79

 exploited

1.78

Activations Density 0.000%

No Known Activations

This feature has no known activations.