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

1:0.05

2:0.09

3:0.10

4:0.08

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

milo

-1.88

idth

-1.77

 repent

-1.68

psey

-1.66

icken

-1.64

jri

-1.61

iddle

-1.61

gently

-1.60

spir

-1.59

aciously

-1.57

POSITIVE LOGITS

OTA

1.87

 Machines

1.71

IUM

1.70

Users

1.67

 Networks

1.67

rams

1.65

ORTS

1.57

}:

1.55

ⓘ

1.55

 Comput

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.