INDEX

Explanations

consecutive uses of the word "that."

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

0:0.03

1:0.03

2:0.09

3:0.10

4:0.02

5:0.04

6:0.07

7:0.13

8:0.13

9:0.16

10:0.10

11:0.04

Negative Logits

ante

-1.09

$$

-1.09

-1.06

eeper

-1.01

requires

-0.96

五

-0.96

-0.95

ensable

-0.95

sers

-0.95

POSITIVE LOGITS

 nostalg

0.98

 Bout

0.96

 TAMADRA

0.93

 Margaret

0.92

 Ending

0.92

 Alic

0.91

 designing

0.91

 ital

0.91

 hypot

0.90

 assass

0.89

Activations Density 0.029%

consecutive uses of the word "that."

No Comments

No Known Activations