INDEX

Explanations

phrases that indicate the basis of arguments or claims

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

New Auto-Interp

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

0:0.02

1:0.01

2:0.09

3:0.05

4:0.17

5:0.02

6:0.05

7:0.35

8:0.02

9:0.04

10:0.07

11:0.07

Negative Logits

�

-1.70

joy

-1.58

龍

-1.58

bill

-1.54

�

-1.53

abbit

-1.52

md

-1.51

osponsors

-1.50

mr

-1.45

jee

-1.45

POSITIVE LOGITS

 inference

1.69

 grounding

1.63

 hypotheses

1.59

 causation

1.58

 conclusive

1.54

 conver

1.52

 theories

1.51

evidence

1.49

 belief

1.49

 inquiry

1.49

Activations Density 0.004%

phrases that indicate the basis of arguments or claims

No Comments

No Known Activations