INDEX

Explanations

phrases related to legal actions and consequences

oai_token-act-pair · gpt-3.5-turbo

references to violence and human rights abuses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Anxiety

-0.77

clinton

-0.76

-0.72

 Cooperative

-0.71

ECO

-0.69

cci

-0.68

nergy

-0.68

 CNBC

-0.66

PAC

-0.66

Customer

-0.65

POSITIVE LOGITS

 executions

1.66

 cruc

1.47

 execution

1.47

 hanged

1.45

 tortured

1.39

 executed

1.39

 crucifix

1.39

 slaughtered

1.38

 decap

1.37

 corpses

1.36

Activations Density 0.441%

phrases related to legal actions and consequences

references to violence and human rights abuses

No Comments

No Known Activations