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

0:0.06

1:0.07

2:0.08

3:0.08

4:0.09

5:0.09

6:0.08

7:0.09

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 indict

-1.88

 unse

-1.66

 deleg

-1.59

 inconven

-1.58

 Miche

-1.57

 misunderstand

-1.56

 inconvenience

-1.56

could

-1.50

 Bradley

-1.49

Render

-1.47

POSITIVE LOGITS

zees

1.98

SPONSORED

1.98

OLOGY

1.92

netic

1.83

 Clicker

1.74

opes

1.73

uminati

1.69

idae

1.67

alk

1.67

atics

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.