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

2:0.08

3:0.09

4:0.08

5:0.08

6:0.07

7:0.09

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

 Legislation

-1.74

channelAvailability

-1.67

Specific

-1.65

 horm

-1.54

 Bleach

-1.51

 liking

-1.49

RL

-1.48

NF

-1.44

 NEVER

-1.42

 Symptoms

-1.41

POSITIVE LOGITS

eria

1.97

)."

1.91

alid

1.81

plet

1.71

──

1.65

arial

1.63

ía

1.63

abor

1.62

elfare

1.62

aco

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.