INDEX

Explanations

negations or phrases indicating denial

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

0:0.08

1:0.10

2:0.09

3:0.07

4:0.08

5:0.07

6:0.07

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

IPS

-1.99

RAY

-1.83

-1.75

plet

-1.74

Reviewer

-1.71

 guiActiveUn

-1.71

フォ

-1.68

 Rena

-1.68

BIL

-1.66

arak

-1.61

POSITIVE LOGITS

 adjacent

1.80

 overhaul

1.74

 stride

1.70

 targeted

1.65

 scrapped

1.64

 periphery

1.62

 recess

1.60

 plurality

1.58

 overlap

1.57

 overlapping

1.56

Activations Density 0.000%

negations or phrases indicating denial

No Comments

No Known Activations