INDEX

Explanations

references to the Quran

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

1:0.08

2:0.08

3:0.09

4:0.08

5:0.09

6:0.06

7:0.08

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

 amnesty

-3.00

 Scots

-2.91

 volunteering

-2.81

 freeing

-2.78

 remission

-2.75

 activism

-2.73

 asylum

-2.71

 improvis

-2.69

esc

-2.65

 cath

-2.65

POSITIVE LOGITS

oshi

3.08

tile

3.06

bul

3.04

ortal

3.04

achi

2.98

Size

2.96

pid

2.96

Item

2.94

ogen

2.92

height

2.90

Activations Density 0.000%

references to the Quran

No Comments

No Known Activations