INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.09

1:0.08

2:0.07

3:0.06

4:0.08

5:0.08

6:0.08

7:0.07

8:0.07

9:0.09

10:0.08

11:0.08

Negative Logits

scrib

-2.06

COR

-1.91

COMPLE

-1.86

 nationwide

-1.85

izable

-1.82

 clans

-1.79

ADVERTISEMENT

-1.78

 commanders

-1.76

Wire

-1.75

KT

-1.75

POSITIVE LOGITS

ache

2.35

obyl

2.20

tar

1.95

bah

1.92

lot

1.92

 Parables

1.92

nea

1.90

oise

1.89

iat

1.85

 headache

1.85

Activations Density 0.000%

No Known Activations

This feature has no known activations.