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

Head Attr Weights

0:0.05

1:0.05

2:0.08

3:0.09

4:0.09

5:0.07

6:0.10

7:0.08

8:0.08

9:0.09

10:0.08

11:0.09

Negative Logits

-2.21

 enthusi

-1.64

acebook

-1.63

halla

-1.57

retty

-1.55

bh

-1.53

 wholes

-1.51

ainers

-1.51

 strengths

-1.50

 remission

-1.48

POSITIVE LOGITS

?),

1.96

?).

1.93

sounding

1.74

>]

1.72

pmwiki

1.65

enario

1.63

ini

1.61

?)

1.59

acher

1.58

eval

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.