INDEX

Explanations

occurrences of the letter 's'

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

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

0:0.02

1:0.03

2:0.21

3:0.09

4:0.12

5:0.06

6:0.14

7:0.04

8:0.02

9:0.03

10:0.08

11:0.10

Negative Logits

pload

-1.69

 innocent

-1.42

 innoc

-1.40

ulence

-1.39

atel

-1.38

 instead

-1.37

pex

-1.36

rhy

-1.35

 proportions

-1.33

 taps

-1.32

POSITIVE LOGITS

MpServer

1.95

athlon

1.65

 Nanto

1.60

 Cooperative

1.59

ropolitan

1.58

University

1.58

 Universities

1.53

Merit

1.44

ecided

1.43

NL

1.41

Activations Density 0.011%

occurrences of the letter 's'

No Comments

No Known Activations