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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.08

9:0.08

10:0.09

11:0.10

Negative Logits

ographies

-2.05

ebook

-2.01

cknow

-1.90

 endors

-1.77

 achie

-1.70

Prep

-1.69

gdala

-1.67

Benef

-1.67

ovie

-1.66

 indo

-1.62

POSITIVE LOGITS

 congestion

1.77

angled

1.64

iably

1.62

 madness

1.60

 typh

1.58

 chaos

1.57

 yawn

1.57

 paralysis

1.57

 sluggish

1.57

string

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.