INDEX

Explanations

URLs associated with political content

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

0:0.04

1:0.03

2:0.16

3:0.07

4:0.09

5:0.05

6:0.09

7:0.11

8:0.03

9:0.05

10:0.15

11:0.06

Negative Logits

ectomy

-1.72

rious

-1.53

aimon

-1.52

ivan

-1.44

 counselors

-1.41

rieve

-1.40

ewitness

-1.40

 warranties

-1.38

unctions

-1.37

 reassure

-1.35

POSITIVE LOGITS

establishment

1.60

govtrack

1.59

→

1.58

clinton

1.52

til

1.40

 Elections

1.40

Republican

1.36

 Opposition

1.36

politics

1.35

 Democratic

1.33

Activations Density 0.000%

URLs associated with political content

No Comments

No Known Activations