INDEX

Explanations

references to connections or relationships between subjects

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

4:0.09

5:0.02

6:0.04

7:0.50

8:0.02

9:0.02

10:0.05

11:0.06

Negative Logits

ONSORED

-1.78

Draft

-1.77

emouth

-1.68

ャ

-1.65

URE

-1.61

eez

-1.59

geist

-1.57

ateurs

-1.55

 VIDEOS

-1.55

REAM

-1.51

POSITIVE LOGITS

 knots

2.38

 knot

2.17

 allegiance

1.80

 ties

1.66

 strand

1.64

 causal

1.63

 causation

1.57

 undo

1.54

tie

1.53

 strings

1.52

Activations Density 0.015%

references to connections or relationships between subjects

No Comments

No Known Activations