INDEX

Explanations

phrases related to causation or consequences

oai_token-act-pair · gpt-3.5-turbo

instances of actions or events that lead to consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

arily

-0.72

 toured

-0.71

 contrace

-0.69

 cared

-0.66

 headed

-0.65

 topped

-0.64

 handled

-0.64

 relied

-0.63

BN

-0.63

 owed

-0.63

POSITIVE LOGITS

 confirmation

0.79

 confusion

0.75

 bloodshed

0.73

 extinction

0.71

 dismissal

0.70

 breakthrough

0.69

 laughter

0.69

 death

0.69

icial

0.68

forth

0.67

Activations Density 0.051%

phrases related to causation or consequences

instances of actions or events that lead to consequences

No Comments

No Known Activations