INDEX

Explanations

punctuation marks and the word "another"

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

0:0.07

1:0.07

2:0.09

3:0.06

4:0.08

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

netflix

-2.89

pmwiki

-2.84

 Sims

-2.80

DS

-2.76

�

-2.76

 Whitman

-2.64

iazep

-2.63

 裏覚醒

-2.62

iframe

-2.58

ブ

-2.58

POSITIVE LOGITS

 promot

3.07

 tending

2.79

 curing

2.77

 marqu

2.75

 marching

2.73

 helicop

2.65

rot

2.63

 keeper

2.59

 bearing

2.58

 weather

2.52

Activations Density 0.000%

punctuation marks and the word "another"

No Comments

No Known Activations