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

2:0.09

3:0.07

4:0.10

5:0.06

6:0.10

7:0.07

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

itans

-1.68

odium

-1.58

lam

-1.57

amphetamine

-1.52

 Californ

-1.51

hetamine

-1.46

 Retrieved

-1.45

veyard

-1.43

encia

-1.40

amia

-1.40

POSITIVE LOGITS

Agent

2.11

 neighb

2.08

 invis

1.81

 horizont

1.74

 Roose

1.66

appropriately

1.61

 perpend

1.59

Together

1.57

robe

1.47

 enthusi

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.