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

0:0.06

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.09

7:0.10

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

 VICE

-1.64

GCC

-1.53

 prejudice

-1.46

TT

-1.44

.>>

-1.42

 debugger

-1.41

 dissent

-1.41

 quant

-1.40

 race

-1.37

 hashtag

-1.36

POSITIVE LOGITS

ゼウス

1.76

ビ

1.66

roman

1.65

kj

1.64

chairs

1.60

abytes

1.58

女

1.54

ール

1.51

ruary

1.51

tumblr

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.