INDEX

Explanations

words related to spin-offs or franchise extensions

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

references to spin-off content in various media forms

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

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

Head Attr Weights

0:0.02

1:0.02

2:0.07

3:0.28

4:0.02

5:0.02

6:0.09

7:0.11

8:0.03

9:0.08

10:0.06

11:0.13

Negative Logits

ailability

-1.46

ufact

-1.44

inguished

-1.41

angered

-1.32

seless

-1.29

ailable

-1.20

onse

-1.20

aughtered

-1.18

undreds

-1.16

amples

-1.15

POSITIVE LOGITS

tsky

1.34

tails

1.15

cycles

1.12

tein

1.11

 saga

1.09

 metaphor

1.09

 weave

1.07

Reloaded

1.05

 medium

1.05

 circles

1.04

Activations Density 0.005%

words related to spin-offs or franchise extensions

references to spin-off content in various media forms

No Known Activations