INDEX

Explanations

concepts related to political dynamics and societal issues

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.01

1:0.01

2:0.06

3:0.06

4:0.33

5:0.03

6:0.03

7:0.26

8:0.04

9:0.03

10:0.05

11:0.04

Negative Logits

draft

-1.77

Draft

-1.74

Redd

-1.67

listed

-1.61

cause

-1.59

lesh

-1.58

Fax

-1.57

sites

-1.54

idav

-1.54

 challeng

-1.53

POSITIVE LOGITS

 Into

1.78

 cues

1.77

 frustrations

1.77

 energies

1.72

 impulses

1.66

 anim

1.61

 frustration

1.53

 Gravity

1.50

 energy

1.49

 imagination

1.49

Activations Density 0.002%

concepts related to political dynamics and societal issues

No Comments

No Known Activations