INDEX

Explanations

occurrences of the word "and"

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

2:0.08

3:0.09

4:0.07

5:0.09

6:0.08

7:0.09

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

 Vaughan

-2.96

 Amsterdam

-2.79

 Vaughn

-2.77

 humour

-2.66

 Melbourne

-2.55

 guest

-2.51

 category

-2.49

sex

-2.45

 advert

-2.44

 Krishna

-2.44

POSITIVE LOGITS

代

2.88

clave

2.83

insula

2.83

ichick

2.80

tnc

2.76

EPA

2.76

ilitary

2.74

TPP

2.72

arag

2.72

↑

2.70

Activations Density 0.000%

occurrences of the word "and"

No Comments

No Known Activations