INDEX

Explanations

instances of the word "to."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.06

2:0.08

3:0.08

4:0.09

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

 Ezek

-1.81

anwhile

-1.73

nown

-1.73

 contacts

-1.72

aneously

-1.69

culosis

-1.69

 Purch

-1.65

 purchases

-1.62

entimes

-1.62

 Relief

-1.60

POSITIVE LOGITS

ctor

1.94

allo

1.80

 procedural

1.70

Honest

1.68

Rule

1.62

olding

1.60

older

1.59

 prejudice

1.56

errors

1.56

 semantics

1.54

Activations Density 0.000%

instances of the word "to."

No Comments

No Known Activations