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

0:0.08

1:0.08

2:0.09

3:0.07

4:0.08

5:0.08

6:0.09

7:0.07

8:0.08

9:0.07

10:0.07

11:0.09

Negative Logits

adelphia

-1.96

ipeg

-1.92

kas

-1.92

��極

-1.82

outhern

-1.82

��

-1.74

vernight

-1.74

wine

-1.73

orney

-1.71

ukemia

-1.71

POSITIVE LOGITS

Catalog

1.97

Yug

1.92

 Mahjong

1.84

 Puzzle

1.74

Boh

1.71

Geh

1.65

 hierarch

1.64

 Frieza

1.55

 Unified

1.55

 outward

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.