INDEX

Explanations

numeric codes or identifiers associated with locations or entities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

0:0.14

1:0.16

2:0.06

3:0.07

4:0.05

5:0.15

6:0.05

7:0.01

8:0.09

9:0.08

10:0.06

11:0.02

Negative Logits

pie

-1.80

gue

-1.71

Fug

-1.70

+.

-1.68

.」

-1.62

 Carnival

-1.59

!.

-1.56

 Tornado

-1.54

 Dogs

-1.53

dor

-1.52

POSITIVE LOGITS

�

1.88

forth

1.82

 carbohyd

1.77

AFTA

1.74

ailable

1.74

requently

1.67

�

1.66

aciously

1.65

ibly

1.65

alks

1.62

Activations Density 0.000%

numeric codes or identifiers associated with locations or entities

No Comments

No Known Activations