INDEX

Explanations

No Explanations Found

New Auto-Interp

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

1:0.09

2:0.07

3:0.08

4:0.09

5:0.06

6:0.08

7:0.06

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

arov

-1.69

 veto

-1.66

 reciproc

-1.61

enton

-1.61

secret

-1.60

Streamer

-1.59

iq

-1.58

eval

-1.57

 deliber

-1.55

 vetoed

-1.54

POSITIVE LOGITS

 Carnage

1.84

 laun

1.70

theless

1.64

yo

1.64

phrine

1.60

 Ezek

1.60

 Beir

1.60

awa

1.59

 enthusi

1.55

 withd

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.