INDEX

Explanations

the word "thereafter"

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

1:0.07

2:0.09

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

ngth

-3.25

================

-2.99

#$#$

-2.85

======

-2.69

 incidental

-2.59

urances

-2.54

Pool

-2.52

Limit

-2.51

inct

-2.47

========

-2.45

POSITIVE LOGITS

 Zionism

3.79

 Juda

3.55

 Rabbi

3.45

 Judaism

3.25

 rabbi

3.17

 Roma

3.10

 Aram

3.05

Zel

2.96

Zy

2.89

 Rwanda

2.88

Activations Density 0.000%

the word "thereafter"

No Comments

No Known Activations