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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.06

2:0.07

3:0.09

4:0.08

5:0.08

6:0.09

7:0.07

8:0.09

9:0.08

10:0.09

11:0.07

Negative Logits

 schematic

-1.78

gebra

-1.69

 Torch

-1.64

 cheers

-1.51

 jokes

-1.51

 illustration

-1.51

 Editorial

-1.50

OTOS

-1.50

 toast

-1.45

 References

-1.45

POSITIVE LOGITS

ahime

1.91

ihad

1.77

netflix

1.70

population

1.66

 twent

1.65

urch

1.61

pmwiki

1.55

cum

1.54

◼

1.54

ploy

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.