INDEX

Explanations

No Explanations Found

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

1:0.09

2:0.08

3:0.07

4:0.08

5:0.08

6:0.07

7:0.07

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

 administering

-1.89

 Morty

-1.85

ateurs

-1.81

 estimating

-1.81

 evaluating

-1.80

 interpreting

-1.75

elist

-1.74

Reviewer

-1.70

pse

-1.70

 distinguishing

-1.67

POSITIVE LOGITS

Gig

1.83

ulk

1.80

oids

1.69

south

1.63

 capacitor

1.59

 caps

1.55

Abs

1.54

的

1.54

solid

1.53

uss

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.