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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.05

2:0.09

3:0.07

4:0.10

5:0.06

6:0.07

7:0.11

8:0.08

9:0.07

10:0.09

11:0.09

Negative Logits

 prevailing

-2.12

 pricing

-1.92

 behav

-1.87

emb

-1.85

 narrowing

-1.79

 behavi

-1.75

 continuing

-1.72

 speculation

-1.70

 widening

-1.66

 insur

-1.63

POSITIVE LOGITS

Desktop

1.70

amins

1.69

 Alpha

1.66

Daily

1.64

House

1.60

itia

1.60

Library

1.60

Machine

1.59

mas

1.56

Beast

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.