INDEX

Explanations

occurrences of the word "of."

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

0:0.07

1:0.08

2:0.08

3:0.08

4:0.08

5:0.10

6:0.09

7:0.06

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 Finder

-2.79

 Scouts

-2.58

Baltimore

-2.58

 Clicker

-2.58

 Route

-2.57

 Sammy

-2.56

 spectator

-2.53

Seattle

-2.53

catch

-2.53

Vision

-2.51

POSITIVE LOGITS

 gobl

3.74

 lawy

3.06

drm

2.84

luaj

2.79

jew

2.75

lain

2.70

cav

2.66

lied

2.65

 manif

2.54

pent

2.52

Activations Density 0.000%

occurrences of the word "of."

No Comments

No Known Activations