INDEX

Explanations

words related to political or geographical context

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.01

2:0.06

3:0.45

4:0.02

5:0.09

6:0.02

7:0.04

8:0.03

9:0.01

10:0.10

11:0.02

Negative Logits

 failures

-2.01

 inspections

-1.97

Testing

-1.93

 pressures

-1.92

 resilience

-1.90

 efforts

-1.89

storms

-1.89

workers

-1.89

 unprepared

-1.86

 shoppers

-1.85

POSITIVE LOGITS

 noun

3.98

 slang

3.72

 surname

3.71

 adjective

3.70

 name

3.67

 abbre

3.66

 phrase

3.60

 suffix

3.60

 nickname

3.43

 descriptor

3.40

Activations Density 1.284%

words related to political or geographical context

No Comments

No Known Activations