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

0:0.09

1:0.06

2:0.09

3:0.08

4:0.09

5:0.08

6:0.08

7:0.08

8:0.08

9:0.06

10:0.07

11:0.08

Negative Logits

Attempt

-2.00

$$$$

-1.88

SPONSORED

-1.88

アル

-1.86

CONCLUS

-1.84

��

-1.77

Secondly

-1.75

lessly

-1.69

WINDOWS

-1.66

 intervening

-1.64

POSITIVE LOGITS

angelo

1.97

obar

1.69

 Royale

1.68

uz

1.67

rb

1.66

akedown

1.65

iro

1.61

ra

1.59

ale

1.59

avi

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.