INDEX

Explanations

phrases related to suspicious or unethical activities

oai_token-act-pair · gpt-3.5-turbo

terms related to suspicious or unethical behavior and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-0.82

effective

-0.81

united

-0.77

oler

-0.77

equal

-0.76

 FranÃ§

-0.74

emis

-0.72

breaker

-0.71

ruary

-0.71

ternally

-0.70

POSITIVE LOGITS

 behaviour

1.52

 behavior

1.50

 behaviors

1.39

 conduct

1.39

 behaviours

1.36

 activities

1.30

 activity

1.28

 practices

1.19

 actions

1.10

 circumstances

1.09

Activations Density 0.153%

phrases related to suspicious or unethical activities

terms related to suspicious or unethical behavior and activities

No Comments

No Known Activations