INDEX

Explanations

terms related to organizations and leadership roles

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_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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.01

2:0.18

3:0.08

4:0.10

5:0.08

6:0.08

7:0.07

8:0.12

9:0.06

10:0.10

11:0.05

Negative Logits

rolet

-1.77

uctions

-1.74

ワン

-1.66

esthesia

-1.61

uers

-1.59

��

-1.46

IRE

-1.46

untled

-1.45

田

-1.45

appings

-1.44

POSITIVE LOGITS

 pinnacle

1.61

 excellence

1.59

 attracting

1.58

 capable

1.51

 unlike

1.50

 affair

1.48

 accompl

1.47

 haven

1.47

 attracts

1.36

.""

1.36

Activations Density 0.174%

terms related to organizations and leadership roles

No Comments

No Known Activations