INDEX

Explanations

contextually significant terms related to decline or decrease

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

0:0.06

1:0.06

2:0.07

3:0.08

4:0.17

5:0.11

6:0.06

7:0.06

8:0.07

9:0.07

10:0.07

11:0.07

Negative Logits

"@

-2.83

SEE

-2.55

ahime

-2.19

atha

-2.19

 Valiant

-2.19

 WRITE

-2.18

 TEXT

-2.18

BAD

-2.17

Eva

-2.16

KE

-2.15

POSITIVE LOGITS

 partisan

2.43

partisan

2.22

 smoking

2.21

phalt

2.17

icultural

2.14

 province

2.12

grades

2.12

 politically

2.12

Disc

2.11

ulin

2.10

Activations Density 0.000%

contextually significant terms related to decline or decrease

No Comments

No Known Activations