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

3:0.06

4:0.08

5:0.10

6:0.07

7:0.08

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

Ame

-1.89

 STATS

-1.84

 Insight

-1.76

 Heroes

-1.69

 Sloan

-1.67

 Baton

-1.64

 acronym

-1.60

 chapter

-1.59

 RAND

-1.58

 Dartmouth

-1.56

POSITIVE LOGITS

rite

1.91

maid

1.87

Required

1.78

itters

1.77

occupied

1.74

orbit

1.73

estate

1.69

hare

1.68

optional

1.68

expensive

1.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.