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

0:0.07

1:0.09

2:0.08

3:0.07

4:0.08

5:0.09

6:0.07

7:0.07

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

—"

-1.91

 whom

-1.79

 schizophren

-1.78

 Sands

-1.76

,—

-1.75

?",

-1.75

 Psychiatry

-1.72

—

-1.70

HS

-1.69

 Khalid

-1.67

POSITIVE LOGITS

retty

2.13

aceous

2.06

ohyd

2.05

atform

1.93

ograp

1.89

ategory

1.89

urtle

1.88

orative

1.86

jug

1.84

ivated

1.81

Activations Density 0.000%

No Known Activations

This feature has no known activations.