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

1:0.10

2:0.07

3:0.11

4:0.08

5:0.08

6:0.06

7:0.06

8:0.06

9:0.10

10:0.08

11:0.08

Negative Logits

���

-2.30

 Watson

-1.92

 Barrett

-1.85

 debunked

-1.76

 Torch

-1.72

 McGu

-1.67

 vanquished

-1.67

 McAuliffe

-1.60

 battled

-1.58

 supplemented

-1.56

POSITIVE LOGITS

illy

2.00

hur

1.90

nah

1.87

inventoryQuantity

1.84

cookie

1.81

 Shame

1.76

フォ

1.75

iche

1.75

OME

1.75

stru

1.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.