INDEX

Explanations

references to political roles or positions

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_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.08

1:0.09

2:0.08

3:0.08

4:0.09

5:0.06

6:0.07

7:0.08

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

Fug

-2.37

asar

-2.28

 Errors

-2.11

avid

-2.05

intel

-2.05

 Conan

-2.04

 Dennis

-2.02

 Imran

-2.01

Kul

-1.99

Nak

-1.98

POSITIVE LOGITS

SPONSORED

3.08

xon

2.50

 convertible

2.14

ATE

2.13

Scroll

2.08

+.

2.08

 capped

2.07

ptive

2.05

votes

2.00

 measurable

1.98

Activations Density 0.000%

references to political roles or positions

No Comments

No Known Activations