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

0:0.08

1:0.09

2:0.09

3:0.07

4:0.09

5:0.06

6:0.09

7:0.08

8:0.08

9:0.07

10:0.07

11:0.07

Negative Logits

loader

-1.84

uberty

-1.78

Pg

-1.73

cig

-1.73

lane

-1.69

 buggy

-1.68

ggle

-1.68

estinal

-1.67

ysis

-1.65

nsics

-1.64

POSITIVE LOGITS

Dom

1.75

 Schwar

1.68

Notable

1.62

 Spirits

1.57

 Rewards

1.52

 Creatures

1.51

Values

1.50

 allocations

1.49

Medium

1.47

 Naval

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.