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

0:0.08

1:0.07

2:0.08

3:0.11

4:0.09

5:0.07

6:0.07

7:0.08

8:0.10

9:0.06

10:0.08

11:0.07

Negative Logits

ibaba

-2.02

growth

-1.99

single

-1.84

 Ripple

-1.74

 forecasting

-1.73

rition

-1.64

Average

-1.61

traditional

-1.59

 ladder

-1.57

ynthesis

-1.57

POSITIVE LOGITS

Fax

1.75

¶

1.72

··

1.61

ctuary

1.59

sburg

1.59

1.57

 site

1.57

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

1.55

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

1.55

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.