INDEX

Explanations

references to entities or subjects in a narrative context

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

1:0.08

2:0.09

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.09

Negative Logits

emp

-2.96

Atl

-2.96

 Siem

-2.84

caps

-2.83

acan

-2.72

 halluc

-2.68

 amput

-2.66

 Erdogan

-2.56

 illiter

-2.55

 Erit

-2.55

POSITIVE LOGITS

 relational

2.97

 Donation

2.87

 Patron

2.84

collect

2.79

swing

2.68

bett

2.68

 Resist

2.64

 Browse

2.56

groups

2.55

RAW

2.46

Activations Density 0.000%

references to entities or subjects in a narrative context

No Comments

No Known Activations