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

1:0.08

2:0.08

3:0.06

4:0.08

5:0.07

6:0.06

7:0.08

8:0.09

9:0.09

10:0.08

11:0.08

Negative Logits

eatures

-1.90

版

-1.75

ohm

-1.74

Features

-1.71

aho

-1.67

Wire

-1.62

utenant

-1.62

iPhone

-1.60

 radar

-1.59

Overview

-1.58

POSITIVE LOGITS

ertodd

1.90

helps

1.87

 membership

1.79

 Camden

1.78

 turnover

1.68

cling

1.64

 admissions

1.62

 Sonia

1.62

bell

1.62

ECB

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.