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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.07

2:0.08

3:0.09

4:0.08

5:0.08

6:0.06

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

taboola

-1.90

blo

-1.74

 mishand

-1.69

cry

-1.67

QC

-1.52

 storms

-1.50

 teasing

-1.48

 vibration

-1.47

uitous

-1.46

generated

-1.45

POSITIVE LOGITS

ntil

2.11

 veter

1.90

edin

1.85

 Volunte

1.81

 Baptist

1.76

 Beir

1.76

FSA

1.72

illas

1.72

alloc

1.68

 Palestin

1.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.