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

0:0.09

1:0.05

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

itored

-1.91

untled

-1.81

utonium

-1.69

cohol

-1.66

ACTED

-1.66

 Sending

-1.57

 Probe

-1.51

omore

-1.50

PsyNetMessage

-1.48

selves

-1.47

POSITIVE LOGITS

 simplicity

1.70

RAG

1.68

 Monkey

1.67

 wonders

1.59

Browser

1.48

hon

1.48

wic

1.47

 motto

1.45

 FANT

1.44

Sim

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.