INDEX

Explanations

negative impacts or consequences

oai_token-act-pair · gpt-3.5-turbo

terms related to negative health impacts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Hide

-0.89

ablished

-0.75

racuse

-0.75

¤

-0.74

LESS

-0.73

bly

-0.72

protect

-0.69

stretched

-0.69

herer

-0.69

bold

-0.68

POSITIVE LOGITS

 consequences

1.49

 effects

1.48

 impacts

1.30

 outcomes

1.30

 repercussions

1.28

 ramifications

1.17

effects

1.16

 affects

1.14

 Effects

1.10

 impact

1.09

Activations Density 0.118%

negative impacts or consequences

terms related to negative health impacts

No Comments

No Known Activations