INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.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

1:0.06

2:0.07

3:0.09

4:0.09

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.07

11:0.09

Negative Logits

▬

-2.16

soType

-1.81

 Alchemy

-1.66

 Scand

-1.66

 ALEC

-1.57

rehens

-1.54

 incomprehensible

-1.48

ENCY

-1.46

 Scotia

-1.45

 persists

-1.44

POSITIVE LOGITS

azeera

1.95

atel

1.95

unal

1.92

atro

1.92

atre

1.91

bash

1.79

oso

1.76

grave

1.73

inea

1.73

alm

1.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.