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

1:0.07

2:0.09

3:0.08

4:0.07

5:0.08

6:0.09

7:0.08

8:0.09

9:0.06

10:0.07

11:0.08

Negative Logits

etheless

-1.77

 eleph

-1.71

arcity

-1.69

 Psychiatric

-1.69

jri

-1.58

 dere

-1.57

 congest

-1.55

 FANTASY

-1.51

LIC

-1.49

 psychiatrist

-1.48

POSITIVE LOGITS

 respectively

1.65

 Fuck

1.65

 stances

1.56

Fuck

1.51

usterity

1.50

reach

1.49

 Proud

1.45

bringer

1.44

wow

1.44

rand

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.