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

1:0.06

2:0.10

3:0.09

4:0.09

5:0.07

6:0.08

7:0.08

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

_>

-1.94

role

-1.69

iri

-1.64

onement

-1.63

tackle

-1.62

 shif

-1.59

arez

-1.56

pillar

-1.56

variable

-1.55

annis

-1.55

POSITIVE LOGITS

 independents

1.92

 FOIA

1.83

 Koen

1.76

 backlog

1.75

��極

1.74

ographers

1.63

 nationwide

1.60

 FISA

1.56

 subscriptions

1.51

 checks

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.