INDEX

Explanations

references to personal or specific experiences related to individuals or events

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.13

1:0.10

2:0.14

3:0.09

4:0.11

5:0.03

6:0.02

7:0.06

8:0.05

9:0.06

10:0.10

11:0.06

Negative Logits

 oneself

-1.06

skirts

-1.04

ichever

-1.01

ording

-1.00

zb

-0.99

orks

-0.97

ievers

-0.96

iever

-0.94

urat

-0.91

holder

-0.91

POSITIVE LOGITS

 counterparts

1.51

 holdings

1.29

 counterpart

1.20

 brethren

1.18

 portfolio

1.16

iasm

1.14

 woes

1.11

 selves

1.06

 haul

1.04

 heritage

1.04

Activations Density 0.719%

references to personal or specific experiences related to individuals or events

No Comments

No Known Activations