INDEX

Explanations

positive or negative descriptors related to behaviors or states

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_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.35

1:0.05

2:0.02

3:0.10

4:0.14

5:0.06

6:0.04

7:0.02

8:0.05

9:0.08

10:0.02

11:0.02

Negative Logits

autions

-1.63

butt

-1.63

 waivers

-1.57

 kisses

-1.51

DF

-1.48

*/(

-1.48

omever

-1.47

 preferably

-1.46

lihood

-1.43

 optionally

-1.41

POSITIVE LOGITS

ateurs

1.79

 Clicker

1.77

oppable

1.71

piring

1.69

 Hebdo

1.69

 agric

1.63

worldly

1.62

rament

1.62

blers

1.60

cient

1.59

Activations Density 0.000%

positive or negative descriptors related to behaviors or states

No Comments

No Known Activations