INDEX

Explanations

mentions of significant achievements or outcomes

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

0:0.08

1:0.09

2:0.09

3:0.08

4:0.07

5:0.08

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

Wax

-2.24

 Greenberg

-2.21

 Yellow

-2.21

�醒

-2.20

 yellow

-2.13

 mustard

-2.11

 beads

-2.11

yx

-2.10

_-_

-2.06

................................

-2.03

POSITIVE LOGITS

 conduc

2.51

cour

2.38

oult

2.18

serving

2.17

ritional

2.09

 athlet

2.08

 stewards

2.08

oided

2.06

 administr

2.05

 endeavor

2.01

Activations Density 0.000%

mentions of significant achievements or outcomes

No Comments

No Known Activations