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

3:0.07

4:0.07

5:0.07

6:0.08

7:0.08

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

 math

-1.88

owl

-1.79

quant

-1.75

efficiency

-1.72

 Related

-1.66

Numbers

-1.62

 Pinterest

-1.60

uitive

-1.60

 Guan

-1.58

 Maxwell

-1.58

POSITIVE LOGITS

rir

1.94

ASED

1.94

Shot

1.85

HAHAHAHA

1.84

fired

1.81

Reloaded

1.80

 ceasefire

1.78

ANY

1.74

 spawned

1.69

lished

1.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.