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

3:0.09

4:0.08

5:0.09

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.06

Negative Logits

aciously

-1.80

irez

-1.66

stable

-1.58

ounced

-1.58

quartered

-1.57

jab

-1.56

akra

-1.56

thritis

-1.55

ually

-1.54

edly

-1.54

POSITIVE LOGITS

��

2.18

ウス

2.18

 interpreting

1.83

 Dating

1.72

 narr

1.64

 interpretation

1.63

 dating

1.61

��

1.59

 interpretations

1.55

 reading

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.