INDEX

Explanations

names of individuals and their affiliations or roles

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.10

1:0.04

2:0.03

3:0.07

4:0.07

5:0.18

6:0.09

7:0.02

8:0.17

9:0.10

10:0.01

11:0.07

Negative Logits

 sacrifices

-1.76

 nudity

-1.75

 achieves

-1.74

 pics

-1.73

etheless

-1.72

 dramas

-1.68

 ideals

-1.68

 disrespect

-1.68

 subjug

-1.67

 deval

-1.67

POSITIVE LOGITS

Senior

2.10

doctoral

2.04

 Associate

2.01

 Fellow

1.97

 consultant

1.96

ector

1.95

 Forensic

1.95

director

1.94

 Assistant

1.92

 Associates

1.91

Activations Density 0.037%

names of individuals and their affiliations or roles

No Comments

No Known Activations