INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

1:0.07

2:0.07

3:0.08

4:0.08

5:0.09

6:0.08

7:0.08

8:0.06

9:0.07

10:0.08

11:0.09

Negative Logits

ascript

-2.73

ouble

-2.57

vantage

-2.12

NESS

-2.07

�

-2.01

itual

-1.96

Tools

-1.92

credit

-1.92

ained

-1.90

angers

-1.89

POSITIVE LOGITS

 titan

2.10

 decom

1.97

 langu

1.96

 debut

1.90

 churn

1.88

 mint

1.88

shr

1.87

 snail

1.85

 squat

1.85

fri

1.83

Activations Density 0.000%

No Known Activations

This feature has no known activations.