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

0:0.08

1:0.08

2:0.09

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.07

9:0.08

10:0.09

11:0.07

Negative Logits

milo

-2.19

 Rubin

-2.05

 tabl

-1.96

Tools

-1.90

/.

-1.83

models

-1.79

 sued

-1.74

 lawsuits

-1.74

 testified

-1.72

Wr

-1.72

POSITIVE LOGITS

 lantern

2.28

�

2.05

escription

2.02

poral

2.00

emption

1.98

スト

1.96

inct

1.91

ohyd

1.88

agall

1.87

 glim

1.87

Activations Density 0.000%

No Known Activations

This feature has no known activations.