INDEX

Explanations

phrases related to causation or explanation

oai_token-act-pair · gpt-3.5-turbo

statements that use causal language to explain facts or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

soDeliveryDate

-0.84

ifies

-0.74

soever

-0.72

Flag

-0.72

FIG

-0.67

ESA

-0.66

Fu

-0.65

iform

-0.65

Sport

-0.65

Gay

-0.64

POSITIVE LOGITS

 lack

0.88

 proximity

0.86

 scarcity

0.85

 cumbers

0.85

 overlap

0.83

 nature

0.83

 shortage

0.83

 constraints

0.81

 surge

0.81

 influx

0.77

Activations Density 0.367%

phrases related to causation or explanation

statements that use causal language to explain facts or conditions

No Comments

No Known Activations