INDEX

Explanations

phrases that indicate financial support or contributions

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.10

2:0.18

3:0.09

4:0.07

5:0.08

6:0.04

7:0.07

8:0.06

9:0.06

10:0.07

11:0.06

Negative Logits

anism

-1.95

unin

-1.89

paio

-1.73

ostic

-1.68

aic

-1.67

ipal

-1.65

iband

-1.63

escription

-1.62

ansen

-1.60

odynamics

-1.60

POSITIVE LOGITS

cup

1.78

 purse

1.69

 cents

1.69

 tablespoon

1.67

 weekday

1.65

 pint

1.63

 Crate

1.63

 Scrib

1.59

($

1.57

 cups

1.56

Activations Density 0.000%

phrases that indicate financial support or contributions

No Comments

No Known Activations