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

1:0.09

2:0.08

3:0.09

4:0.07

5:0.07

6:0.08

7:0.07

8:0.10

9:0.09

10:0.06

11:0.07

Negative Logits

amera

-2.10

 unspecified

-1.81

nance

-1.78

 eject

-1.70

 --------------------

-1.68

 unstable

-1.66

sed

-1.65

 disorderly

-1.63

stable

-1.63

 endanger

-1.63

POSITIVE LOGITS

��

2.66

Reviewer

2.04

ゴン

2.03

aceutical

1.94

ð

1.92

humans

1.80

 Archdemon

1.80

��

1.79

pring

1.79

okia

1.77

Activations Density 0.000%

No Known Activations

This feature has no known activations.