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

1:0.07

2:0.07

3:0.07

4:0.09

5:0.09

6:0.07

7:0.06

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

audi

-2.36

Smart

-2.06

Republic

-2.01

Nation

-1.95

Best

-1.85

Rev

-1.84

plus

-1.82

Made

-1.80

umm

-1.78

Eye

-1.77

POSITIVE LOGITS

 analogy

1.83

 parentheses

1.82

BILITIES

1.77

 dismissing

1.61

 summoning

1.59

FIG

1.57

 contempt

1.56

 sidelines

1.56

 adjourn

1.56

lees

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.