INDEX

Explanations

phrases indicating consideration or evaluation

oai_token-act-pair · gpt-3.5-turbo

references to considering or weighing various factors in decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

sis

-0.86

soever

-0.74

heres

-0.74

sil

-0.73

nect

-0.70

jer

-0.69

Constructed

-0.68

edition

-0.66

bey

-0.66

jac

-0.66

POSITIVE LOGITS

 factors

0.97

 considerations

0.95

 mitigating

0.83

 probabilities

0.79

enance

0.77

how

0.74

 budgetary

0.71

 whether

0.70

 factor

0.70

ancy

0.70

Activations Density 0.065%

phrases indicating consideration or evaluation

references to considering or weighing various factors in decision-making

No Comments

No Known Activations