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

0:0.07

1:0.11

2:0.09

3:0.08

4:0.08

5:0.06

6:0.08

7:0.08

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

��

-1.81

 uncom

-1.68

jamin

-1.60

dq

-1.59

 offline

-1.52

 filings

-1.50

 derailed

-1.50

 Coulter

-1.47

 stalled

-1.46

printf

-1.46

POSITIVE LOGITS

OOOO

1.93

onomy

1.85

');

1.83

umbn

1.74

.")

1.73

gor

1.71

EEEE

1.70

oms

1.70

agascar

1.70

OOOOOOOO

1.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.