INDEX

Explanations

the word "this."

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.08

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.07

9:0.09

10:0.08

11:0.07

Negative Logits

 certific

-2.71

 horm

-2.66

 monop

-2.61

 Chambers

-2.58

ACT

-2.54

Eur

-2.50

 hops

-2.48

 Columb

-2.45

 regulated

-2.44

 Bore

-2.42

POSITIVE LOGITS

amily

3.44

ithing

3.01

ettel

2.89

qqa

2.89

ettings

2.84

hetamine

2.72

aeper

2.71

chwitz

2.63

 Weiner

2.63

ails

2.62

Activations Density 0.000%

the word "this."

No Comments

No Known Activations