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

0:0.06

1:0.06

2:0.09

3:0.09

4:0.07

5:0.07

6:0.08

7:0.12

8:0.06

9:0.07

10:0.09

11:0.08

Negative Logits

 behav

-1.56

 prospects

-1.54

 prospect

-1.54

tha

-1.49

 util

-1.49

etheless

-1.49

 sugg

-1.47

 remem

-1.46

 misunder

-1.45

 spectators

-1.45

POSITIVE LOGITS

alty

1.76

Oy

1.59

Nor

1.54

arium

1.53

Vote

1.48

Paper

1.47

renheit

1.47

oy

1.45

Leader

1.45

proof

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.