INDEX

Explanations

references to notable individuals and their actions or statements

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.05

1:0.03

2:0.05

3:0.04

4:0.06

5:0.46

6:0.03

7:0.03

8:0.03

9:0.12

10:0.04

11:0.03

Negative Logits

inge

-2.71

fficient

-2.38

ordable

-2.38

coming

-2.29

asses

-2.14

urable

-2.11

 unbeat

-2.11

arag

-2.09

ifiable

-2.08

ieties

-1.99

POSITIVE LOGITS

Instead

6.11

 instead

5.53

 Instead

5.44

Nevertheless

5.17

 Rather

5.11

instead

5.07

Nonetheless

4.98

Rather

4.92

 nevertheless

4.65

 rather

4.49

Activations Density 0.277%

references to notable individuals and their actions or statements

No Comments

No Known Activations